Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0264. Min Act: -0.0000

Data Index: 1337528 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0230. Min Act: -0.0000

Data Index: 645396 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1303040 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0216. Min Act: -0.0000

Data Index: 1333900 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0223. Min Act: -0.0000

Data Index: 175714 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1147426 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0239. Min Act: -0.0000

Data Index: 570621 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0203. Min Act: -0.0000

Data Index: 1244180 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0189. Min Act: -0.0000

Data Index: 990900 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0193. Min Act: -0.0000

Data Index: 1500766 (Python Code)

Max Activating Token Index: 535

Text #10

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1528997 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0183. Min Act: -0.0000

Data Index: 1262650 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0207. Min Act: -0.0000

Data Index: 1052806 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0193. Min Act: -0.0000

Data Index: 1449393 (Python Code)

Max Activating Token Index: 922

Text #14

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0200. Min Act: -0.0000

Data Index: 139837 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0183. Min Act: -0.0000

Data Index: 709911 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0187. Min Act: -0.0000

Data Index: 1216333 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0176. Min Act: -0.0000

Data Index: 523784 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1400318 (Python Code)

Max Activating Token Index: 327

Text #19

Max Range: 0.0264. Min Range: -0.0264

Max Act: 0.0195. Min Act: -0.0000

Data Index: 690309 (C4 (Web Text))

Max Activating Token Index: 295