Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3257 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1184716 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0251. Min Act: -0.0003

Data Index: 436871 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0254. Min Act: -0.0003

Data Index: 676034 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1245492 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0242. Min Act: -0.0003

Data Index: 67951 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0240. Min Act: -0.0003

Data Index: 677893 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0217. Min Act: -0.0003

Data Index: 45212 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0228. Min Act: -0.0003

Data Index: 84546 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0227. Min Act: -0.0003

Data Index: 272039 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0241. Min Act: -0.0003

Data Index: 513742 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0231. Min Act: -0.0003

Data Index: 537586 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0217. Min Act: -0.0003

Data Index: 480088 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1348043 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0219. Min Act: -0.0003

Data Index: 408653 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0223. Min Act: -0.0003

Data Index: 743756 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0220. Min Act: -0.0003

Data Index: 739473 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1359517 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0219. Min Act: -0.0003

Data Index: 1179687 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1022482 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.0278. Min Range: -0.0278

Max Act: 0.0215. Min Act: -0.0003

Data Index: 705928 (C4 (Web Text))

Max Activating Token Index: 950