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

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

Neuron 3535 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0189. Min Act: -0.0003

Data Index: 894554 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0003

Data Index: 647678 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0180. Min Act: -0.0003

Data Index: 600040 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1082714 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0184. Min Act: -0.0003

Data Index: 795061 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0181. Min Act: -0.0003

Data Index: 985428 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0170. Min Act: -0.0003

Data Index: 960862 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0168. Min Act: -0.0003

Data Index: 781136 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1204082 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0167. Min Act: -0.0003

Data Index: 246821 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1034862 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0165. Min Act: -0.0003

Data Index: 914501 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0164. Min Act: -0.0003

Data Index: 790394 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0160. Min Act: -0.0003

Data Index: 865455 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1321750 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0164. Min Act: -0.0003

Data Index: 406168 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1044492 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0165. Min Act: -0.0003

Data Index: 955794 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1095414 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0152. Min Act: -0.0003

Data Index: 196589 (C4 (Web Text))

Max Activating Token Index: 684