Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 974 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1118384 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0242. Min Act: -0.0004

Data Index: 249651 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0241. Min Act: -0.0004

Data Index: 633602 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0241. Min Act: -0.0005

Data Index: 1059712 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0239. Min Act: -0.0005

Data Index: 491194 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0237. Min Act: -0.0004

Data Index: 1149737 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0237. Min Act: -0.0005

Data Index: 73989 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0236. Min Act: -0.0004

Data Index: 6233 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1228875 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0235. Min Act: -0.0004

Data Index: 624482 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0229. Min Act: -0.0005

Data Index: 919711 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0234. Min Act: -0.0005

Data Index: 1109970 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0233. Min Act: -0.0005

Data Index: 519646 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0231. Min Act: -0.0005

Data Index: 664337 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0005

Data Index: 739436 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0004

Data Index: 133895 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0235. Min Act: -0.0005

Data Index: 1122173 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0226. Min Act: -0.0004

Data Index: 1287163 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0231. Min Act: -0.0005

Data Index: 242085 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0230. Min Act: -0.0004

Data Index: 1279606 (C4 (Web Text))

Max Activating Token Index: 26