Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 525 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0205. Min Act: -0.0006

Data Index: 141564 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0183. Min Act: -0.0006

Data Index: 289966 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0173. Min Act: -0.0006

Data Index: 11970 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0161. Min Act: -0.0006

Data Index: 880375 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0171. Min Act: -0.0006

Data Index: 353876 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0166. Min Act: -0.0006

Data Index: 1166170 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0165. Min Act: -0.0006

Data Index: 357561 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0171. Min Act: -0.0006

Data Index: 82416 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1304389 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0170. Min Act: -0.0006

Data Index: 434823 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0157. Min Act: -0.0006

Data Index: 749924 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0160. Min Act: -0.0006

Data Index: 544723 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0167. Min Act: -0.0005

Data Index: 445924 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0163. Min Act: -0.0006

Data Index: 245717 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0165. Min Act: -0.0006

Data Index: 837603 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0158. Min Act: -0.0006

Data Index: 489103 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0159. Min Act: -0.0006

Data Index: 521480 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0163. Min Act: -0.0006

Data Index: 37378 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0154. Min Act: -0.0006

Data Index: 72504 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0205. Min Range: -0.0205

Max Act: 0.0159. Min Act: -0.0006

Data Index: 530951 (C4 (Web Text))

Max Activating Token Index: 611