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

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

Neuron 3257 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1502846 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1614686 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1486619 (Python Code)

Max Activating Token Index: 266

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1383713 (Python Code)

Max Activating Token Index: 111

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1365478 (Python Code)

Max Activating Token Index: 369

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1393132 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1614345 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0202. Min Act: -0.0003

Data Index: 1516450 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1642014 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1454944 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1390258 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1507531 (Python Code)

Max Activating Token Index: 864

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1637690 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1421997 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1604122 (Python Code)

Max Activating Token Index: 282

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1439544 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1650514 (Python Code)

Max Activating Token Index: 734

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0175. Min Act: -0.0003

Data Index: 760965 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1613440 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1525247 (Python Code)

Max Activating Token Index: 529