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

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

Neuron 1424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0002

Data Index: 806774 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0449. Min Act: -0.0002

Data Index: 559896 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1009718 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1254654 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0367. Min Act: -0.0002

Data Index: 620639 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0363. Min Act: -0.0002

Data Index: 953563 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0377. Min Act: -0.0002

Data Index: 769370 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0357. Min Act: -0.0002

Data Index: 374657 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1278492 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0359. Min Act: -0.0002

Data Index: 446695 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0355. Min Act: -0.0002

Data Index: 819612 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1034980 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0361. Min Act: -0.0002

Data Index: 932210 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0344. Min Act: -0.0002

Data Index: 687478 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0338. Min Act: -0.0002

Data Index: 513092 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0365. Min Act: -0.0002

Data Index: 573980 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0358. Min Act: -0.0002

Data Index: 408309 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0344. Min Act: -0.0002

Data Index: 704068 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0341. Min Act: -0.0002

Data Index: 277690 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0317. Min Act: -0.0002

Data Index: 67899 (C4 (Web Text))

Max Activating Token Index: 95