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

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

Neuron 3713 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1083212 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0259. Min Act: -0.0002

Data Index: 319970 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0198. Min Act: -0.0002

Data Index: 663468 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1011184 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1021715 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0192. Min Act: -0.0002

Data Index: 135231 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0187. Min Act: -0.0002

Data Index: 239519 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0181. Min Act: -0.0002

Data Index: 229327 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0182. Min Act: -0.0002

Data Index: 311866 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0166. Min Act: -0.0002

Data Index: 351344 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1222756 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0173. Min Act: -0.0002

Data Index: 310025 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0156. Min Act: -0.0002

Data Index: 101640 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0170. Min Act: -0.0002

Data Index: 558036 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0178. Min Act: -0.0002

Data Index: 347635 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0160. Min Act: -0.0002

Data Index: 745034 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1016581 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0158. Min Act: -0.0002

Data Index: 846750 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0141. Min Act: -0.0002

Data Index: 883560 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0153. Min Act: -0.0002

Data Index: 121057 (C4 (Web Text))

Max Activating Token Index: 7