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

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

Neuron 4395 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: 0.0326. Min Range: -0.0326

Max Act: 0.0306. Min Act: -0.0002

Data Index: 452729 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0003

Data Index: 227365 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0257. Min Act: -0.0003

Data Index: 188736 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1344840 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0291. Min Act: -0.0003

Data Index: 517148 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1181115 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0263. Min Act: -0.0003

Data Index: 97720 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0248. Min Act: -0.0003

Data Index: 298593 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0247. Min Act: -0.0002

Data Index: 62560 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0236. Min Act: -0.0003

Data Index: 96782 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1315824 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0230. Min Act: -0.0003

Data Index: 855719 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1256405 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0229. Min Act: -0.0002

Data Index: 344756 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0228. Min Act: -0.0003

Data Index: 137332 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0239. Min Act: -0.0003

Data Index: 308208 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1312418 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0231. Min Act: -0.0003

Data Index: 812071 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1267371 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0222. Min Act: -0.0002

Data Index: 49908 (C4 (Web Text))

Max Activating Token Index: 339