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

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

Neuron 50 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0315. Min Act: -0.0006

Data Index: 355029 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0315. Min Act: -0.0006

Data Index: 1005260 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1296441 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0297. Min Act: -0.0006

Data Index: 612548 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0274. Min Act: -0.0006

Data Index: 1148155 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0278. Min Act: -0.0006

Data Index: 146540 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0291. Min Act: -0.0006

Data Index: 223393 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0275. Min Act: -0.0006

Data Index: 605546 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0281. Min Act: -0.0006

Data Index: 1119149 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0268. Min Act: -0.0005

Data Index: 1066027 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0295. Min Act: -0.0006

Data Index: 846846 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0284. Min Act: -0.0005

Data Index: 711865 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1012780 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0280. Min Act: -0.0006

Data Index: 69619 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0275. Min Act: -0.0006

Data Index: 308466 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1034449 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0273. Min Act: -0.0006

Data Index: 713820 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1324115 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1405539 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 0.0315. Min Range: -0.0315

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1187442 (C4 (Web Text))

Max Activating Token Index: 879