Understanding how Transformer-based Language Models (LMs) learn and recall information is a key goal of the deep learning community. Recent interpretability methods project weights and hidden states obtained from the forward pass to the models’ vocabularies, helping to uncover how information flows within LMs. In this work, we extend this methodology to LMs’ backward pass and gradients. We first prove that a gradient matrix can be cast as a low-rank linear combination of its forward and backward passes’ inputs. We then develop methods to project these gradients into vocabulary items and explore the mechanics of how new information is stored in the LMs’ neurons.

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM attention heads and memory values, the vectors the models dynamically create and recall while processing a given input. By analyzing the tokens they represent through this projection, we identify patterns in the information flow inside the attention mechanism. Based on our discoveries, we create a tool to visualize a forward pass of Generative Pre-trained Transformers (GPTs) as an interactive flow graph, with nodes representing neurons or hidden states and edges representing the interactions between them. Our visualization simplifies huge amounts of data into easy-to-read plots that can reflect the models’ internal processing, uncovering the contribution of each component to the models’ final prediction. Our visualization also unveils new insights about the role of layer norms as semantic filters that influence the models’ output, and about neurons that are always activated during forward passes and act as regularization vectors.