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

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

Neuron 32 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0301. Min Act: -0.0006

Data Index: 724404 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0270. Min Act: -0.0006

Data Index: 463278 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0269. Min Act: -0.0006

Data Index: 1032509 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1198987 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0268. Min Act: -0.0006

Data Index: 600313 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0251. Min Act: -0.0006

Data Index: 285614 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1008393 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1272038 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0258. Min Act: -0.0006

Data Index: 996094 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0255. Min Act: -0.0006

Data Index: 196481 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0260. Min Act: -0.0006

Data Index: 82918 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0240. Min Act: -0.0006

Data Index: 221366 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0245. Min Act: -0.0006

Data Index: 1079941 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0239. Min Act: -0.0006

Data Index: 602001 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0237. Min Act: -0.0006

Data Index: 57159 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0236. Min Act: -0.0006

Data Index: 446937 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0247. Min Act: -0.0006

Data Index: 273964 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0240. Min Act: -0.0006

Data Index: 1091412 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1180605 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0238. Min Act: -0.0006

Data Index: 995801 (C4 (Web Text))

Max Activating Token Index: 78