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

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

Neuron 2010 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4351. Min Act: -0.0002

Data Index: 976006 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.4334. Min Act: -0.0002

Data Index: 18967 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3866. Min Act: -0.0002

Data Index: 948980 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3867. Min Act: -0.0002

Data Index: 512087 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3790. Min Act: -0.0002

Data Index: 1333032 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3531. Min Act: -0.0002

Data Index: 701564 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3455. Min Act: -0.0002

Data Index: 802551 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3484. Min Act: -0.0002

Data Index: 1048137 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3125. Min Act: -0.0002

Data Index: 345336 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3258. Min Act: -0.0002

Data Index: 1280470 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3233. Min Act: -0.0002

Data Index: 441440 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3143. Min Act: -0.0002

Data Index: 1122356 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3209. Min Act: -0.0002

Data Index: 975279 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3185. Min Act: -0.0002

Data Index: 1245592 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3054. Min Act: -0.0002

Data Index: 101110 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3168. Min Act: -0.0002

Data Index: 260201 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3063. Min Act: -0.0002

Data Index: 1005816 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3106. Min Act: -0.0002

Data Index: 1207505 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3121. Min Act: -0.0002

Data Index: 682584 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.4351. Min Range: -0.4351

Max Act: 0.3101. Min Act: -0.0002

Data Index: 630504 (C4 (Web Text))

Max Activating Token Index: 368