Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1376 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0002

Data Index: 175507 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0465. Min Act: -0.0002

Data Index: 698016 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0429. Min Act: -0.0002

Data Index: 780293 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0415. Min Act: -0.0002

Data Index: 899820 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1090176 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0379. Min Act: -0.0002

Data Index: 880643 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0344. Min Act: -0.0002

Data Index: 363986 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0351. Min Act: -0.0002

Data Index: 52714 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1190148 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0340. Min Act: -0.0002

Data Index: 752784 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1273459 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0330. Min Act: -0.0002

Data Index: 860780 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0315. Min Act: -0.0002

Data Index: 935749 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0314. Min Act: -0.0002

Data Index: 738434 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0297. Min Act: -0.0002

Data Index: 789039 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1042055 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0284. Min Act: -0.0002

Data Index: 460004 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0296. Min Act: -0.0002

Data Index: 238728 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1058496 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0292. Min Act: -0.0002

Data Index: 473635 (C4 (Web Text))

Max Activating Token Index: 842