Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5094 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1358524 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0490. Min Act: -0.0003

Data Index: 79288 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1157714 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0409. Min Act: -0.0003

Data Index: 528536 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0417. Min Act: -0.0003

Data Index: 275480 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1039908 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0393. Min Act: -0.0003

Data Index: 628954 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0380. Min Act: -0.0002

Data Index: 427898 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1300111 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0386. Min Act: -0.0002

Data Index: 947533 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0380. Min Act: -0.0003

Data Index: 396327 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0370. Min Act: -0.0002

Data Index: 510437 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0374. Min Act: -0.0003

Data Index: 525916 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0364. Min Act: -0.0003

Data Index: 667142 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0373. Min Act: -0.0003

Data Index: 564285 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0367. Min Act: -0.0003

Data Index: 306732 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1168750 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0369. Min Act: -0.0003

Data Index: 2717 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1224780 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0370. Min Act: -0.0003

Data Index: 361688 (C4 (Web Text))

Max Activating Token Index: 138