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

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

Neuron 1844 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: 0.0364. Min Range: -0.0364

Max Act: 0.0364. Min Act: -0.0006

Data Index: 235529 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0349. Min Act: -0.0005

Data Index: 1063577 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0342. Min Act: -0.0005

Data Index: 844698 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0347. Min Act: -0.0006

Data Index: 94184 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0324. Min Act: -0.0006

Data Index: 303736 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0334. Min Act: -0.0006

Data Index: 324263 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0331. Min Act: -0.0006

Data Index: 945498 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0325. Min Act: -0.0006

Data Index: 728588 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0330. Min Act: -0.0006

Data Index: 961793 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0318. Min Act: -0.0006

Data Index: 532714 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0343. Min Act: -0.0006

Data Index: 1138838 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0316. Min Act: -0.0006

Data Index: 656636 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0316. Min Act: -0.0006

Data Index: 744641 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0322. Min Act: -0.0006

Data Index: 967743 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0312. Min Act: -0.0006

Data Index: 52587 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0311. Min Act: -0.0006

Data Index: 774005 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0327. Min Act: -0.0006

Data Index: 1040417 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0315. Min Act: -0.0006

Data Index: 319820 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0309. Min Act: -0.0006

Data Index: 794885 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.0364. Min Range: -0.0364

Max Act: 0.0302. Min Act: -0.0006

Data Index: 539182 (C4 (Web Text))

Max Activating Token Index: 494