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

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

Neuron 109 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: 0.0563. Min Range: -0.0563

Max Act: 0.0563. Min Act: -0.0003

Data Index: 653262 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0456. Min Act: -0.0002

Data Index: 537655 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0457. Min Act: -0.0003

Data Index: 198090 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0441. Min Act: -0.0003

Data Index: 58602 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1033490 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0447. Min Act: -0.0003

Data Index: 500179 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0427. Min Act: -0.0003

Data Index: 9041 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0443. Min Act: -0.0003

Data Index: 1128639 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0416. Min Act: -0.0003

Data Index: 718852 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0428. Min Act: -0.0003

Data Index: 69696 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0415. Min Act: -0.0003

Data Index: 137883 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0415. Min Act: -0.0003

Data Index: 386188 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0428. Min Act: -0.0003

Data Index: 855876 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0404. Min Act: -0.0003

Data Index: 348719 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0400. Min Act: -0.0003

Data Index: 1117836 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0413. Min Act: -0.0003

Data Index: 505799 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0402. Min Act: -0.0003

Data Index: 382855 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0401. Min Act: -0.0003

Data Index: 810667 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0379. Min Act: -0.0003

Data Index: 906520 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.0563. Min Range: -0.0563

Max Act: 0.0397. Min Act: -0.0002

Data Index: 158262 (C4 (Web Text))

Max Activating Token Index: 238