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

Dataset: The Pile

Neuron 4392 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.7230. Min Act: -0.0000

Data Index: 1313183 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.4555. Min Act: -0.0000

Data Index: 460999 (The Pile)

Max Activating Token Index: 466

Text #2

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3529. Min Act: -0.0000

Data Index: 1896981 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.2491. Min Act: -0.0000

Data Index: 621180 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3645. Min Act: -0.0000

Data Index: 350102 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.2719. Min Act: -0.0000

Data Index: 1993935 (The Pile)

Max Activating Token Index: 303

Text #6

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1801450 (The Pile)

Max Activating Token Index: 636

Text #7

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1418200 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.2657. Min Act: -0.0000

Data Index: 1956028 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3459. Min Act: -0.0000

Data Index: 860282 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.3061. Min Act: -0.0000

Data Index: 502419 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1740. Min Act: -0.0000

Data Index: 842494 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1959993 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1308. Min Act: -0.0000

Data Index: 976915 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1176. Min Act: -0.0000

Data Index: 955460 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1830. Min Act: -0.0000

Data Index: 123447 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1905. Min Act: -0.0000

Data Index: 1649397 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1515290 (The Pile)

Max Activating Token Index: 438

Text #18

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1283486 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 1.7230. Min Range: -1.7230

Max Act: 1.1357. Min Act: -0.0000

Data Index: 591771 (The Pile)

Max Activating Token Index: 340