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

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

Neuron 3627 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: 0.0514. Min Range: -0.0514

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1337172 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0512. Min Act: -0.0003

Data Index: 773217 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0506. Min Act: -0.0002

Data Index: 496062 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0482. Min Act: -0.0003

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1020436 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0496. Min Act: -0.0003

Data Index: 871260 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0457. Min Act: -0.0002

Data Index: 380294 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0444. Min Act: -0.0003

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0422. Min Act: -0.0003

Data Index: 51545 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0436. Min Act: -0.0003

Data Index: 908365 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0403. Min Act: -0.0003

Data Index: 593003 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0405. Min Act: -0.0003

Data Index: 449412 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0383. Min Act: -0.0003

Data Index: 280227 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0383. Min Act: -0.0003

Data Index: 253181 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0389. Min Act: -0.0003

Data Index: 381378 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0387. Min Act: -0.0003

Data Index: 857548 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0380. Min Act: -0.0003

Data Index: 702942 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0364. Min Act: -0.0002

Data Index: 859387 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0376. Min Act: -0.0002

Data Index: 270727 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0514. Min Range: -0.0514

Max Act: 0.0367. Min Act: -0.0003

Data Index: 497759 (C4 (Web Text))

Max Activating Token Index: 679