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

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

Neuron 629 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1236358 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0403. Min Act: 0.0000

Data Index: 218288 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0306. Min Act: -0.0001

Data Index: 409650 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1107328 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0251. Min Act: -0.0000

Data Index: 458738 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1314345 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0237. Min Act: -0.0000

Data Index: 336616 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0236. Min Act: -0.0001

Data Index: 437296 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0254. Min Act: -0.0000

Data Index: 132874 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0260. Min Act: -0.0001

Data Index: 602817 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0239. Min Act: -0.0001

Data Index: 36723 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0255. Min Act: -0.0001

Data Index: 278576 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0240. Min Act: -0.0001

Data Index: 445466 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0223. Min Act: -0.0001

Data Index: 785916 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0228. Min Act: -0.0000

Data Index: 954268 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1174955 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0225. Min Act: -0.0001

Data Index: 848686 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0223. Min Act: -0.0001

Data Index: 447744 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0208. Min Act: -0.0001

Data Index: 318186 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0202. Min Act: -0.0001

Data Index: 17779 (C4 (Web Text))

Max Activating Token Index: 715