Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3928 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.8362. Min Act: -0.0000

Data Index: 970655 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6416. Min Act: -0.0000

Data Index: 680963 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6196. Min Act: -0.0000

Data Index: 836239 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5959. Min Act: -0.0000

Data Index: 43698 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6389. Min Act: -0.0001

Data Index: 342312 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6128. Min Act: -0.0000

Data Index: 837988 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1030262 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5336. Min Act: -0.0000

Data Index: 305816 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1099307 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5272. Min Act: -0.0000

Data Index: 966015 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5284. Min Act: -0.0000

Data Index: 86300 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1091601 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5154. Min Act: -0.0000

Data Index: 366336 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5351. Min Act: -0.0000

Data Index: 310802 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.5092. Min Act: -0.0000

Data Index: 333683 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1024972 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4982. Min Act: -0.0000

Data Index: 107165 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4646. Min Act: -0.0001

Data Index: 736501 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4404. Min Act: -0.0001

Data Index: 62321 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.8362. Min Range: -0.8362

Max Act: 0.4590. Min Act: -0.0000

Data Index: 178732 (C4 (Web Text))

Max Activating Token Index: 356