Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3756 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0513. Min Act: -0.0003

Data Index: 174548 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0497. Min Act: -0.0003

Data Index: 984793 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0467. Min Act: -0.0003

Data Index: 547767 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0426. Min Act: -0.0003

Data Index: 514707 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0434. Min Act: -0.0003

Data Index: 617229 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0402. Min Act: -0.0003

Data Index: 319305 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0361. Min Act: -0.0003

Data Index: 986276 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0398. Min Act: -0.0003

Data Index: 954366 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0381. Min Act: -0.0003

Data Index: 301718 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0363. Min Act: -0.0003

Data Index: 758249 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1187416 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0380. Min Act: -0.0003

Data Index: 201848 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0373. Min Act: -0.0003

Data Index: 402886 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1257555 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0355. Min Act: -0.0003

Data Index: 126407 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0358. Min Act: -0.0003

Data Index: 982944 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0376. Min Act: -0.0003

Data Index: 714426 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0356. Min Act: -0.0003

Data Index: 997646 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0341. Min Act: -0.0003

Data Index: 896173 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0513. Min Range: -0.0513

Max Act: 0.0323. Min Act: -0.0003

Data Index: 705358 (C4 (Web Text))

Max Activating Token Index: 616