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

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

Neuron 1552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0360. Min Act: -0.0003

Data Index: 418090 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0003

Data Index: 972340 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1191845 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0351. Min Act: -0.0003

Data Index: 20710 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0362. Min Act: -0.0003

Data Index: 701493 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0341. Min Act: -0.0003

Data Index: 959281 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1325718 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0338. Min Act: -0.0003

Data Index: 792100 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0353. Min Act: -0.0003

Data Index: 826725 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1182271 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0338. Min Act: -0.0004

Data Index: 697094 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0329. Min Act: -0.0004

Data Index: 594753 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0347. Min Act: -0.0003

Data Index: 431400 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0333. Min Act: -0.0003

Data Index: 380163 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0325. Min Act: -0.0003

Data Index: 632874 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0339. Min Act: -0.0004

Data Index: 91907 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0336. Min Act: -0.0003

Data Index: 452200 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0324. Min Act: -0.0003

Data Index: 828588 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0324. Min Act: -0.0003

Data Index: 985943 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0325. Min Act: -0.0003

Data Index: 622482 (C4 (Web Text))

Max Activating Token Index: 26