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

Dataset: The Pile

Neuron 1113 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1005092 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.4031. Min Act: -0.0000

Data Index: 473610 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1775624 (The Pile)

Max Activating Token Index: 881

Text #3

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.1958. Min Act: -0.0000

Data Index: 121553 (The Pile)

Max Activating Token Index: 339

Text #4

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.2233. Min Act: -0.0000

Data Index: 10682 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1442705 (The Pile)

Max Activating Token Index: 705

Text #6

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.1242. Min Act: -0.0000

Data Index: 1311024 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0498. Min Act: -0.0000

Data Index: 1041787 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0051. Min Act: -0.0000

Data Index: 939594 (The Pile)

Max Activating Token Index: 288

Text #9

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0050. Min Act: -0.0000

Data Index: 826399 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1006188 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0015. Min Act: -0.0000

Data Index: 415453 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1262883 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1586413 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0296. Min Act: -0.0000

Data Index: 116639 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1953708 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1550310 (The Pile)

Max Activating Token Index: 824

Text #17

Max Range: 1.4508. Min Range: -1.4508

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1953532 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1879494 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 1.4508. Min Range: -1.4508

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1247104 (The Pile)

Max Activating Token Index: 750