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

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

Neuron 4762 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: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1132703 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0232. Min Act: -0.0002

Data Index: 595593 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0236. Min Act: -0.0002

Data Index: 987489 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1379944 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1654624 (Python Code)

Max Activating Token Index: 797

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1073931 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1601428 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1030721 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0196. Min Act: -0.0002

Data Index: 377148 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1239691 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0201. Min Act: -0.0002

Data Index: 480487 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1653698 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0201. Min Act: -0.0002

Data Index: 390947 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0198. Min Act: -0.0002

Data Index: 578230 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0188. Min Act: -0.0002

Data Index: 682396 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0187. Min Act: -0.0002

Data Index: 647494 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0187. Min Act: -0.0002

Data Index: 289268 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1630127 (Python Code)

Max Activating Token Index: 255

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0185. Min Act: -0.0002

Data Index: 681287 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0180. Min Act: -0.0002

Data Index: 893453 (C4 (Web Text))

Max Activating Token Index: 689