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

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

Neuron 1475 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: 0.0334. Min Range: -0.0334

Max Act: 0.0334. Min Act: -0.0005

Data Index: 565967 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0295. Min Act: -0.0005

Data Index: 725812 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0303. Min Act: -0.0005

Data Index: 777947 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0293. Min Act: -0.0005

Data Index: 141699 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0287. Min Act: -0.0005

Data Index: 71293 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0270. Min Act: -0.0005

Data Index: 906698 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0280. Min Act: -0.0005

Data Index: 571859 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0280. Min Act: -0.0005

Data Index: 531564 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0278. Min Act: -0.0005

Data Index: 266669 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0005

Data Index: 84472 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0273. Min Act: -0.0005

Data Index: 417649 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0279. Min Act: -0.0005

Data Index: 523663 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0265. Min Act: -0.0005

Data Index: 276852 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0277. Min Act: -0.0005

Data Index: 515776 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0277. Min Act: -0.0005

Data Index: 719630 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1277658 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0264. Min Act: -0.0005

Data Index: 344271 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0263. Min Act: -0.0005

Data Index: 494170 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0269. Min Act: -0.0005

Data Index: 946431 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.0334. Min Range: -0.0334

Max Act: 0.0274. Min Act: -0.0005

Data Index: 690110 (C4 (Web Text))

Max Activating Token Index: 238