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

Dataset: The Pile

Neuron 4547 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2848. Min Act: -0.0000

Data Index: 510745 (The Pile)

Max Activating Token Index: 918

Text #1

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2966. Min Act: -0.0000

Data Index: 647490 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2561. Min Act: -0.0000

Data Index: 688024 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2755. Min Act: -0.0000

Data Index: 175586 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2727. Min Act: -0.0000

Data Index: 1136366 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2513. Min Act: -0.0000

Data Index: 873582 (The Pile)

Max Activating Token Index: 515

Text #6

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2605. Min Act: -0.0000

Data Index: 941598 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2579. Min Act: -0.0000

Data Index: 441052 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2651. Min Act: -0.0000

Data Index: 609170 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2168. Min Act: -0.0000

Data Index: 576053 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.1857. Min Act: -0.0000

Data Index: 336046 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2473. Min Act: -0.0000

Data Index: 51402 (The Pile)

Max Activating Token Index: 488

Text #12

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1534820 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1650584 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2256. Min Act: -0.0000

Data Index: 148696 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2259. Min Act: -0.0000

Data Index: 138357 (The Pile)

Max Activating Token Index: 982

Text #16

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2187. Min Act: -0.0000

Data Index: 690831 (The Pile)

Max Activating Token Index: 816

Text #17

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1519237 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2244. Min Act: -0.0000

Data Index: 342358 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1956696 (The Pile)

Max Activating Token Index: 638