Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 241 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: -0.0006

Data Index: 535474 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0512. Min Act: -0.0006

Data Index: 629630 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0513. Min Act: -0.0006

Data Index: 1150874 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0502. Min Act: -0.0006

Data Index: 454504 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0470. Min Act: -0.0006

Data Index: 695720 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0447. Min Act: -0.0006

Data Index: 578011 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0431. Min Act: -0.0006

Data Index: 208099 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0430. Min Act: -0.0006

Data Index: 25104 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0406. Min Act: -0.0006

Data Index: 1251835 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0399. Min Act: -0.0006

Data Index: 1208786 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1109350 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0375. Min Act: -0.0006

Data Index: 523196 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0381. Min Act: -0.0006

Data Index: 1275861 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0374. Min Act: -0.0006

Data Index: 534139 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0373. Min Act: -0.0006

Data Index: 1252403 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0387. Min Act: -0.0006

Data Index: 481881 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0376. Min Act: -0.0006

Data Index: 609215 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0366. Min Act: -0.0006

Data Index: 1223051 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0366. Min Act: -0.0006

Data Index: 648839 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0359. Min Act: -0.0006

Data Index: 180776 (C4 (Web Text))

Max Activating Token Index: 164