Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1042 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0381. Min Act: -0.0004

Data Index: 699001 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0379. Min Act: -0.0003

Data Index: 492096 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0369. Min Act: -0.0003

Data Index: 657121 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0364. Min Act: -0.0004

Data Index: 1272048 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0376. Min Act: -0.0003

Data Index: 732196 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0358. Min Act: -0.0003

Data Index: 499003 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0345. Min Act: -0.0003

Data Index: 206846 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0352. Min Act: -0.0002

Data Index: 743209 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0352. Min Act: -0.0004

Data Index: 758858 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0352. Min Act: -0.0003

Data Index: 82703 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0346. Min Act: -0.0004

Data Index: 36532 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1269274 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0352. Min Act: -0.0003

Data Index: 114933 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0345. Min Act: -0.0003

Data Index: 651254 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0356. Min Act: -0.0004

Data Index: 1027791 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0336. Min Act: -0.0003

Data Index: 756918 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0340. Min Act: -0.0004

Data Index: 1134310 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1231327 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0346. Min Act: -0.0003

Data Index: 961740 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0345. Min Act: -0.0003

Data Index: 796817 (C4 (Web Text))

Max Activating Token Index: 493