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

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

Neuron 3138 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: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0002

Data Index: 644028 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0237. Min Act: -0.0002

Data Index: 793087 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0236. Min Act: -0.0002

Data Index: 959979 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0236. Min Act: -0.0002

Data Index: 609296 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0234. Min Act: -0.0002

Data Index: 856523 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0229. Min Act: -0.0002

Data Index: 870218 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1128457 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0229. Min Act: -0.0002

Data Index: 446318 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0229. Min Act: -0.0002

Data Index: 832876 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1529486 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1499809 (Python Code)

Max Activating Token Index: 538

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0228. Min Act: -0.0002

Data Index: 308339 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1537306 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0226. Min Act: -0.0002

Data Index: 421587 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0226. Min Act: -0.0002

Data Index: 719966 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0225. Min Act: -0.0002

Data Index: 763963 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0224. Min Act: -0.0002

Data Index: 34149 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1364849 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0223. Min Act: -0.0002

Data Index: 566956 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1248257 (C4 (Web Text))

Max Activating Token Index: 271