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

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

Neuron 4097 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: 0.0281. Min Range: -0.0281

Max Act: 0.0281. Min Act: -0.0002

Data Index: 701726 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1401893 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0267. Min Act: -0.0002

Data Index: 418593 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1035806 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1454056 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1365922 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1403242 (Python Code)

Max Activating Token Index: 277

Text #7

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1425099 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0228. Min Act: -0.0002

Data Index: 718349 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0225. Min Act: -0.0002

Data Index: 564670 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0220. Min Act: -0.0002

Data Index: 146586 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0218. Min Act: -0.0002

Data Index: 275989 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1365049 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0198. Min Act: -0.0002

Data Index: 740529 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0199. Min Act: -0.0002

Data Index: 110050 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1120849 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1090370 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0204. Min Act: -0.0002

Data Index: 25538 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0195. Min Act: -0.0002

Data Index: 193723 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.0281. Min Range: -0.0281

Max Act: 0.0186. Min Act: -0.0002

Data Index: 181003 (C4 (Web Text))

Max Activating Token Index: 622