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

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

Neuron 150 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: 0.0243. Min Range: -0.0243

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1514379 (Python Code)

Max Activating Token Index: 59

Text #1

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0185. Min Act: -0.0003

Data Index: 186817 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0190. Min Act: -0.0003

Data Index: 544134 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0181. Min Act: -0.0003

Data Index: 117826 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0201. Min Act: -0.0003

Data Index: 517868 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0191. Min Act: -0.0003

Data Index: 312455 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0185. Min Act: -0.0003

Data Index: 78700 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1048852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0192. Min Act: -0.0003

Data Index: 424892 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0183. Min Act: -0.0003

Data Index: 732163 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1206749 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0177. Min Act: -0.0003

Data Index: 926327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1091174 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0170. Min Act: -0.0003

Data Index: 402370 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0171. Min Act: -0.0003

Data Index: 313214 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1258613 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1176502 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0121. Min Act: -0.0003

Data Index: 88650 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0112. Min Act: -0.0003

Data Index: 382892 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.0243. Min Range: -0.0243

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1088275 (C4 (Web Text))

Max Activating Token Index: 612