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

Dataset: The Pile

Neuron 4411 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: 5.5912. Min Range: -5.5912

Max Act: 5.5912. Min Act: 0.0000

Data Index: 903621 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 5.5912. Min Range: -5.5912

Max Act: 4.7375. Min Act: -0.0000

Data Index: 490784 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 5.5912. Min Range: -5.5912

Max Act: 5.2032. Min Act: 0.0000

Data Index: 339982 (The Pile)

Max Activating Token Index: 737

Text #3

Max Range: 5.5912. Min Range: -5.5912

Max Act: 4.5281. Min Act: -0.0000

Data Index: 526776 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 5.5912. Min Range: -5.5912

Max Act: 4.2190. Min Act: -0.0000

Data Index: 45810 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.9594. Min Act: -0.0000

Data Index: 1110988 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.9640. Min Act: -0.0000

Data Index: 228580 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 5.5912. Min Range: -5.5912

Max Act: 4.2047. Min Act: -0.0000

Data Index: 651696 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 5.5912. Min Range: -5.5912

Max Act: 4.0157. Min Act: -0.0000

Data Index: 97946 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.8585. Min Act: -0.0000

Data Index: 22833 (The Pile)

Max Activating Token Index: 725

Text #10

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.9690. Min Act: -0.0000

Data Index: 789618 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.8683. Min Act: -0.0000

Data Index: 1662226 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.7464. Min Act: -0.0000

Data Index: 62968 (The Pile)

Max Activating Token Index: 308

Text #13

Max Range: 5.5912. Min Range: -5.5912

Max Act: 4.0300. Min Act: -0.0000

Data Index: 1061676 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.7035. Min Act: -0.0000

Data Index: 1753732 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.8982. Min Act: -0.0000

Data Index: 280406 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.6806. Min Act: -0.0000

Data Index: 1516500 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.8415. Min Act: -0.0000

Data Index: 206229 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.7346. Min Act: -0.0000

Data Index: 394352 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 5.5912. Min Range: -5.5912

Max Act: 3.6849. Min Act: -0.0000

Data Index: 1553755 (The Pile)

Max Activating Token Index: 787