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

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

Neuron 446 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0316. Min Act: -0.0001

Data Index: 455077 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0280. Min Act: -0.0001

Data Index: 735627 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1155456 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0001

Data Index: 386252 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0227. Min Act: -0.0001

Data Index: 92024 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0226. Min Act: -0.0001

Data Index: 890712 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0202. Min Act: -0.0001

Data Index: 405886 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0214. Min Act: -0.0001

Data Index: 304030 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1154091 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1229072 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0200. Min Act: -0.0001

Data Index: 812322 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0192. Min Act: -0.0001

Data Index: 222616 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0209. Min Act: -0.0001

Data Index: 1175789 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0207. Min Act: -0.0001

Data Index: 611327 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0185. Min Act: -0.0001

Data Index: 233824 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1257472 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0182. Min Act: -0.0001

Data Index: 1312229 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1332697 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0186. Min Act: -0.0001

Data Index: 205260 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.0316. Min Range: -0.0316

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1132500 (C4 (Web Text))

Max Activating Token Index: 134