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

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

Neuron 3294 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0229. Min Act: -0.0003

Data Index: 545471 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1149180 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0223. Min Act: -0.0003

Data Index: 903614 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0216. Min Act: -0.0003

Data Index: 536193 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0200. Min Act: -0.0003

Data Index: 820097 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0210. Min Act: -0.0003

Data Index: 789545 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0204. Min Act: -0.0003

Data Index: 909477 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0201. Min Act: -0.0003

Data Index: 993731 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0200. Min Act: -0.0003

Data Index: 657416 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1173054 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0196. Min Act: -0.0003

Data Index: 402245 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1162196 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0189. Min Act: -0.0003

Data Index: 460568 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1112451 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0193. Min Act: -0.0003

Data Index: 169139 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0183. Min Act: -0.0002

Data Index: 759866 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0185. Min Act: -0.0003

Data Index: 904820 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0191. Min Act: -0.0003

Data Index: 687626 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1258532 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1571646 (Python Code)

Max Activating Token Index: 64