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

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

Neuron 4351 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0237. Min Act: -0.0002

Data Index: 907856 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0232. Min Act: -0.0002

Data Index: 724373 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0222. Min Act: -0.0002

Data Index: 967995 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0219. Min Act: -0.0002

Data Index: 446701 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0214. Min Act: -0.0002

Data Index: 759735 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1099988 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0222. Min Act: -0.0002

Data Index: 716321 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0217. Min Act: -0.0002

Data Index: 983181 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0216. Min Act: -0.0002

Data Index: 271817 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0215. Min Act: -0.0002

Data Index: 215521 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1354764 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1030000 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 91320 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1300662 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1431971 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1269326 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1272681 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 294305 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 806201 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.0237. Min Range: -0.0237

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1321501 (C4 (Web Text))

Max Activating Token Index: 258