Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1351 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0473. Min Act: -0.0003

Data Index: 968869 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0457. Min Act: -0.0003

Data Index: 136366 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0451. Min Act: -0.0003

Data Index: 443030 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1189337 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0448. Min Act: -0.0003

Data Index: 525458 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0390. Min Act: -0.0003

Data Index: 259911 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0379. Min Act: -0.0003

Data Index: 514294 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1439350 (Python Code)

Max Activating Token Index: 411

Text #8

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0392. Min Act: -0.0003

Data Index: 900948 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0406. Min Act: -0.0003

Data Index: 125073 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0381. Min Act: -0.0003

Data Index: 633460 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0398. Min Act: -0.0003

Data Index: 741174 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0398. Min Act: -0.0003

Data Index: 21831 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0398. Min Act: -0.0003

Data Index: 482664 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1037637 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0370. Min Act: -0.0003

Data Index: 188723 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1079760 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0377. Min Act: -0.0003

Data Index: 296788 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0368. Min Act: -0.0003

Data Index: 880632 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0359. Min Act: -0.0003

Data Index: 163781 (C4 (Web Text))

Max Activating Token Index: 436