Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1249 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0283. Min Act: -0.0001

Data Index: 238278 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0253. Min Act: -0.0001

Data Index: 868851 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0258. Min Act: -0.0001

Data Index: 1626221 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0258. Min Act: -0.0001

Data Index: 230337 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1162548 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1260943 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1367310 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0256. Min Act: -0.0001

Data Index: 938341 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0250. Min Act: -0.0001

Data Index: 551343 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0243. Min Act: -0.0001

Data Index: 109272 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1134331 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1608732 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1641466 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1284384 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0228. Min Act: -0.0002

Data Index: 170711 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0227. Min Act: -0.0002

Data Index: 910220 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1649522 (Python Code)

Max Activating Token Index: 474

Text #17

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0215. Min Act: -0.0001

Data Index: 528308 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1396096 (Python Code)

Max Activating Token Index: 797

Text #19

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0217. Min Act: -0.0002

Data Index: 313450 (C4 (Web Text))

Max Activating Token Index: 910