Follow a token through a transformer
Each token has a row of four numbers. Select a token to follow its row; select a number to see its calculation.
One causal attention head, one pre-normalized block, eight vocabulary tokens. The fixed, invented weights have not learned language.
Change the input
Numbered columns are features, not words. Shapes describe the full matrix; the strips below follow the selected row.
Token and position
Attention mixes positions
Add the attention update
Feed-forward transforms this row
Add the feed-forward update
Scores for the next token
Choose the next token
Choosing the largest probability is a decoding rule. Appending runs the same model on the longer input; the weights stay fixed. This example holds at most eight positions.
See all token rows and fixed parameter tables
Activations change with the input. Parameters stay fixed in this example. In a trained model, training would adjust these parameters.