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

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

Neuron 3647 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0002

Data Index: 227038 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1010282 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0464. Min Act: -0.0002

Data Index: 302855 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1094557 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1058456 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0421. Min Act: -0.0002

Data Index: 450138 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0410. Min Act: -0.0002

Data Index: 563127 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1111397 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0412. Min Act: -0.0002

Data Index: 348150 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0411. Min Act: -0.0002

Data Index: 812920 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0409. Min Act: -0.0002

Data Index: 866244 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0409. Min Act: -0.0002

Data Index: 699313 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1300549 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0407. Min Act: -0.0002

Data Index: 366407 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0413. Min Act: -0.0002

Data Index: 653265 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0400. Min Act: -0.0002

Data Index: 462857 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0397. Min Act: -0.0001

Data Index: 600432 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0391. Min Act: -0.0002

Data Index: 719932 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0389. Min Act: -0.0002

Data Index: 413705 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0389. Min Act: -0.0002

Data Index: 964910 (C4 (Web Text))

Max Activating Token Index: 415