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

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

Neuron 1775 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0005

Data Index: 607902 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0278. Min Act: -0.0005

Data Index: 739558 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1318735 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0240. Min Act: -0.0005

Data Index: 861525 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0238. Min Act: -0.0005

Data Index: 1268889 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0235. Min Act: -0.0005

Data Index: 1402465 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0220. Min Act: -0.0005

Data Index: 467786 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0210. Min Act: -0.0005

Data Index: 394997 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0230. Min Act: -0.0005

Data Index: 528365 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0226. Min Act: -0.0005

Data Index: 395603 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0196. Min Act: -0.0005

Data Index: 165183 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0225. Min Act: -0.0005

Data Index: 24830 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0225. Min Act: -0.0005

Data Index: 1609562 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0221. Min Act: -0.0005

Data Index: 608353 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0210. Min Act: -0.0005

Data Index: 1155314 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0215. Min Act: -0.0005

Data Index: 1196856 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0212. Min Act: -0.0005

Data Index: 735027 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0218. Min Act: -0.0005

Data Index: 856064 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0215. Min Act: -0.0005

Data Index: 422996 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0213. Min Act: -0.0005

Data Index: 155818 (C4 (Web Text))

Max Activating Token Index: 950