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

Dataset: The Pile

Neuron 3388 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: 1.3274. Min Range: -1.3274

Max Act: 1.3274. Min Act: -0.0000

Data Index: 583202 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9757. Min Act: -0.0000

Data Index: 665392 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8971. Min Act: -0.0000

Data Index: 356168 (The Pile)

Max Activating Token Index: 773

Text #3

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8346. Min Act: -0.0000

Data Index: 297486 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8406. Min Act: -0.0000

Data Index: 692693 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1213416 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1967829 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8850. Min Act: -0.0000

Data Index: 363439 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8568. Min Act: -0.0000

Data Index: 358487 (The Pile)

Max Activating Token Index: 296

Text #9

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8055. Min Act: -0.0000

Data Index: 811869 (The Pile)

Max Activating Token Index: 983

Text #10

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.6566. Min Act: -0.0000

Data Index: 823942 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7853. Min Act: -0.0000

Data Index: 938612 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1209439 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7459. Min Act: -0.0000

Data Index: 740518 (The Pile)

Max Activating Token Index: 580

Text #14

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1503007 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7623. Min Act: -0.0000

Data Index: 153575 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7171. Min Act: -0.0000

Data Index: 449453 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1852642 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8256. Min Act: -0.0000

Data Index: 693847 (The Pile)

Max Activating Token Index: 383

Text #19

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.7860. Min Act: -0.0001

Data Index: 101314 (The Pile)

Max Activating Token Index: 973