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

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

Neuron 1625 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: 0.0359. Min Range: -0.0359

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1062832 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0356. Min Act: -0.0002

Data Index: 99654 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0315. Min Act: -0.0002

Data Index: 95782 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0318. Min Act: -0.0002

Data Index: 754362 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0318. Min Act: -0.0002

Data Index: 216234 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1256598 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1270322 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0295. Min Act: -0.0003

Data Index: 150160 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0292. Min Act: -0.0002

Data Index: 752578 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0291. Min Act: -0.0002

Data Index: 418378 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0290. Min Act: -0.0003

Data Index: 933247 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0287. Min Act: -0.0002

Data Index: 40947 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0293. Min Act: -0.0002

Data Index: 255442 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1243252 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1343113 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0279. Min Act: -0.0003

Data Index: 605838 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1047711 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0271. Min Act: -0.0003

Data Index: 231953 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0281. Min Act: -0.0003

Data Index: 586775 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.0359. Min Range: -0.0359

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1314649 (C4 (Web Text))

Max Activating Token Index: 435