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

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

Neuron 1932 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0296. Min Act: -0.0002

Data Index: 331412 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0002

Data Index: 58553 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0296. Min Act: -0.0002

Data Index: 288970 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0311. Min Act: -0.0002

Data Index: 946719 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0273. Min Act: -0.0002

Data Index: 290017 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0268. Min Act: -0.0002

Data Index: 65293 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0282. Min Act: -0.0002

Data Index: 954572 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1036157 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0232. Min Act: -0.0002

Data Index: 779132 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1060996 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0239. Min Act: -0.0002

Data Index: 38707 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0259. Min Act: -0.0002

Data Index: 682662 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1120174 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1081341 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1177928 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1019708 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0265. Min Act: -0.0002

Data Index: 265793 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1489868 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1050246 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0285. Min Act: -0.0002

Data Index: 267644 (C4 (Web Text))

Max Activating Token Index: 220