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

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

Neuron 0 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: 0.0262. Min Range: -0.0262

Max Act: 0.0262. Min Act: -0.0003

Data Index: 795859 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0250. Min Act: -0.0004

Data Index: 731625 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0229. Min Act: -0.0003

Data Index: 56967 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0224. Min Act: -0.0003

Data Index: 486076 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0223. Min Act: -0.0003

Data Index: 108724 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0220. Min Act: -0.0003

Data Index: 556675 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0214. Min Act: -0.0003

Data Index: 609714 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0199. Min Act: -0.0003

Data Index: 414248 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0207. Min Act: -0.0003

Data Index: 933154 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1233822 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1422827 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0189. Min Act: -0.0003

Data Index: 236971 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0199. Min Act: -0.0003

Data Index: 866355 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0177. Min Act: -0.0003

Data Index: 95297 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0195. Min Act: -0.0003

Data Index: 15704 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1632133 (Python Code)

Max Activating Token Index: 454

Text #16

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0198. Min Act: -0.0003

Data Index: 482222 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1373911 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1287416 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.0262. Min Range: -0.0262

Max Act: 0.0181. Min Act: -0.0003

Data Index: 890728 (C4 (Web Text))

Max Activating Token Index: 372