Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2021 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.9027. Min Act: -0.0000

Data Index: 387939 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1432017 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1947531 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8974. Min Act: -0.0000

Data Index: 605431 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8248. Min Act: -0.0000

Data Index: 464172 (The Pile)

Max Activating Token Index: 256

Text #5

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7713. Min Act: -0.0000

Data Index: 102236 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8666. Min Act: -0.0000

Data Index: 887604 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1603140 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8479. Min Act: -0.0000

Data Index: 895707 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7568. Min Act: -0.0000

Data Index: 891496 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7639. Min Act: -0.0000

Data Index: 779545 (The Pile)

Max Activating Token Index: 966

Text #11

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1690643 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1657803 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7582. Min Act: -0.0000

Data Index: 1836445 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7244. Min Act: -0.0000

Data Index: 211464 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7633. Min Act: -0.0000

Data Index: 804503 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1329212 (The Pile)

Max Activating Token Index: 97

Text #17

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7134. Min Act: -0.0000

Data Index: 444711 (The Pile)

Max Activating Token Index: 321

Text #18

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6565. Min Act: -0.0000

Data Index: 907425 (The Pile)

Max Activating Token Index: 836

Text #19

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1915507 (The Pile)

Max Activating Token Index: 562