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

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

Neuron 3460 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: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0003

Data Index: 919317 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1025219 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1098860 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0389. Min Act: -0.0002

Data Index: 298739 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0383. Min Act: -0.0002

Data Index: 138987 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0363. Min Act: -0.0003

Data Index: 637804 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1169260 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1158896 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0357. Min Act: -0.0003

Data Index: 370474 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0356. Min Act: -0.0003

Data Index: 135817 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1357261 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1000109 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0336. Min Act: -0.0003

Data Index: 752383 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0334. Min Act: -0.0003

Data Index: 13834 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0330. Min Act: -0.0003

Data Index: 700418 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0334. Min Act: -0.0003

Data Index: 441963 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0336. Min Act: -0.0003

Data Index: 743432 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0331. Min Act: -0.0002

Data Index: 192493 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1350989 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0332. Min Act: -0.0003

Data Index: 924052 (C4 (Web Text))

Max Activating Token Index: 611