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

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

Neuron 4583 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0002

Data Index: 1612868 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0236. Min Act: -0.0002

Data Index: 245388 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0218. Min Act: -0.0002

Data Index: 880944 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1011524 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1115050 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0215. Min Act: -0.0002

Data Index: 325225 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0215. Min Act: -0.0002

Data Index: 942761 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0216. Min Act: -0.0002

Data Index: 393749 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1239798 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0209. Min Act: -0.0002

Data Index: 190786 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0209. Min Act: -0.0002

Data Index: 420682 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0208. Min Act: -0.0002

Data Index: 893290 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0200. Min Act: -0.0002

Data Index: 403216 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0200. Min Act: -0.0002

Data Index: 944763 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1287927 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0196. Min Act: -0.0002

Data Index: 45138 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1146615 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1067163 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1029084 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0196. Min Act: -0.0002

Data Index: 303664 (C4 (Web Text))

Max Activating Token Index: 18