Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 371 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0247. Min Act: -0.0003

Data Index: 234407 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0191. Min Act: -0.0003

Data Index: 999274 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0185. Min Act: -0.0003

Data Index: 439713 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0170. Min Act: -0.0003

Data Index: 145491 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0176. Min Act: -0.0003

Data Index: 72661 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0178. Min Act: -0.0003

Data Index: 495076 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1204046 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1507307 (Python Code)

Max Activating Token Index: 792

Text #8

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1116297 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0159. Min Act: -0.0003

Data Index: 705830 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1045120 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1626972 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0160. Min Act: -0.0003

Data Index: 373120 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0168. Min Act: -0.0003

Data Index: 921087 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0159. Min Act: -0.0003

Data Index: 656184 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0160. Min Act: -0.0003

Data Index: 507334 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0161. Min Act: -0.0003

Data Index: 498601 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0142. Min Act: -0.0003

Data Index: 116665 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1537069 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 0.0247. Min Range: -0.0247

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1585836 (Python Code)

Max Activating Token Index: 205