Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1601605 (Python Code)

Max Activating Token Index: 621

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0238. Min Act: -0.0002

Data Index: 900998 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1457356 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1103496 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0208. Min Act: -0.0002

Data Index: 586281 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0221. Min Act: -0.0002

Data Index: 1610350 (Python Code)

Max Activating Token Index: 566

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1515174 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1623777 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0206. Min Act: -0.0002

Data Index: 425453 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0209. Min Act: -0.0002

Data Index: 347745 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1484786 (Python Code)

Max Activating Token Index: 460

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1319694 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0174. Min Act: -0.0002

Data Index: 135872 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1520188 (Python Code)

Max Activating Token Index: 418

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1601715 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0190. Min Act: -0.0002

Data Index: 101874 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1428785 (Python Code)

Max Activating Token Index: 49

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1402094 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1141344 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0193. Min Act: -0.0002

Data Index: 624607 (C4 (Web Text))

Max Activating Token Index: 442