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

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

Neuron 737 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: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0006

Data Index: 122272 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0166. Min Act: -0.0006

Data Index: 209012 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1307747 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0172. Min Act: -0.0006

Data Index: 680225 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0165. Min Act: -0.0005

Data Index: 438947 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0164. Min Act: -0.0006

Data Index: 401812 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1358483 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1046320 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0164. Min Act: -0.0006

Data Index: 861629 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0160. Min Act: -0.0006

Data Index: 193595 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1004067 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0158. Min Act: -0.0006

Data Index: 242661 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1130241 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0160. Min Act: -0.0006

Data Index: 447834 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0154. Min Act: -0.0006

Data Index: 140987 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1101777 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0157. Min Act: -0.0006

Data Index: 937391 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1159759 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0150. Min Act: -0.0006

Data Index: 812401 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1319268 (C4 (Web Text))

Max Activating Token Index: 955