Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 182 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3283. Min Act: -0.0002

Data Index: 584464 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3257. Min Act: -0.0002

Data Index: 937431 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3223. Min Act: -0.0002

Data Index: 1348532 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3214. Min Act: -0.0002

Data Index: 1234397 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3196. Min Act: -0.0002

Data Index: 698002 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3194. Min Act: -0.0002

Data Index: 1344629 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3219. Min Act: -0.0002

Data Index: 1194056 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3218. Min Act: -0.0002

Data Index: 869013 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3204. Min Act: -0.0002

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3221. Min Act: -0.0002

Data Index: 276200 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3201. Min Act: -0.0002

Data Index: 804776 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3233. Min Act: -0.0002

Data Index: 1250042 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3187. Min Act: -0.0002

Data Index: 876848 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3212. Min Act: -0.0002

Data Index: 774937 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3189. Min Act: -0.0002

Data Index: 1195894 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3208. Min Act: -0.0002

Data Index: 1141403 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3202. Min Act: -0.0002

Data Index: 1055215 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3200. Min Act: -0.0002

Data Index: 1003856 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3181. Min Act: -0.0002

Data Index: 578263 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.3283. Min Range: -0.3283

Max Act: 0.3190. Min Act: -0.0002

Data Index: 107021 (C4 (Web Text))

Max Activating Token Index: 23