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

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

Neuron 2391 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0000

Data Index: 245425 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0234. Min Act: -0.0000

Data Index: 600265 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0210. Min Act: -0.0000

Data Index: 1409100 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0221. Min Act: -0.0000

Data Index: 838367 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0220. Min Act: -0.0000

Data Index: 388953 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0226. Min Act: -0.0000

Data Index: 175211 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1221828 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0215. Min Act: -0.0000

Data Index: 1107691 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1049851 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1300591 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0220. Min Act: -0.0000

Data Index: 148734 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0207. Min Act: -0.0000

Data Index: 968122 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0214. Min Act: -0.0000

Data Index: 928178 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0221. Min Act: -0.0000

Data Index: 255782 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0213. Min Act: -0.0000

Data Index: 129163 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0207. Min Act: -0.0000

Data Index: 707810 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0207. Min Act: -0.0000

Data Index: 814723 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0208. Min Act: 0.0000

Data Index: 1503968 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0205. Min Act: -0.0000

Data Index: 40846 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0204. Min Act: -0.0000

Data Index: 548028 (C4 (Web Text))

Max Activating Token Index: 210