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

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

Neuron 126 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: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0005

Data Index: 1316842 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0278. Min Act: -0.0005

Data Index: 391617 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0278. Min Act: -0.0005

Data Index: 27884 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0265. Min Act: -0.0005

Data Index: 1319186 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0256. Min Act: -0.0005

Data Index: 308162 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0252. Min Act: -0.0005

Data Index: 41043 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0249. Min Act: -0.0005

Data Index: 422810 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0244. Min Act: -0.0005

Data Index: 565450 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0245. Min Act: -0.0005

Data Index: 369250 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0237. Min Act: -0.0005

Data Index: 977826 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0005

Data Index: 1060384 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0228. Min Act: -0.0005

Data Index: 611353 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0251. Min Act: -0.0005

Data Index: 497433 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0245. Min Act: -0.0005

Data Index: 495141 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1423871 (Python Code)

Max Activating Token Index: 177

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0005

Data Index: 1190846 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0225. Min Act: -0.0005

Data Index: 1235218 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0005

Data Index: 913335 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0238. Min Act: -0.0004

Data Index: 873654 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0233. Min Act: -0.0005

Data Index: 1176988 (C4 (Web Text))

Max Activating Token Index: 653