Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2781 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0002

Data Index: 441487 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1333164 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0226. Min Act: -0.0002

Data Index: 267113 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1159624 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1591514 (Python Code)

Max Activating Token Index: 580

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1442582 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0212. Min Act: -0.0002

Data Index: 980689 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0207. Min Act: -0.0002

Data Index: 183999 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0209. Min Act: -0.0002

Data Index: 712940 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1445051 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1564388 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1628882 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0202. Min Act: -0.0002

Data Index: 371059 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0202. Min Act: -0.0003

Data Index: 691843 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0199. Min Act: -0.0002

Data Index: 935813 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1475061 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0196. Min Act: -0.0002

Data Index: 136631 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1544861 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0194. Min Act: -0.0002

Data Index: 356398 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1572608 (Python Code)

Max Activating Token Index: 588