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

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

Neuron 1388 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: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0002

Data Index: 659411 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0217. Min Act: -0.0002

Data Index: 824822 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0213. Min Act: -0.0002

Data Index: 240987 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0212. Min Act: -0.0002

Data Index: 883338 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0211. Min Act: -0.0002

Data Index: 248775 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0210. Min Act: -0.0002

Data Index: 727054 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0208. Min Act: -0.0002

Data Index: 332795 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0205. Min Act: -0.0002

Data Index: 131146 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0205. Min Act: -0.0002

Data Index: 135547 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1198050 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0208. Min Act: -0.0002

Data Index: 13567 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0203. Min Act: -0.0002

Data Index: 533369 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0202. Min Act: -0.0002

Data Index: 471420 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0206. Min Act: -0.0002

Data Index: 896984 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0202. Min Act: -0.0002

Data Index: 401821 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0202. Min Act: -0.0002

Data Index: 939104 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1178707 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0200. Min Act: -0.0002

Data Index: 502525 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0002

Data Index: 140588 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0199. Min Act: -0.0002

Data Index: 791392 (C4 (Web Text))

Max Activating Token Index: 564