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

Dataset: The Pile

Neuron 105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.5626. Min Act: -0.0000

Data Index: 365794 (The Pile)

Max Activating Token Index: 879

Text #1

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1116107 (The Pile)

Max Activating Token Index: 891

Text #2

Max Range: 1.5626. Min Range: -1.5626

Max Act: 1.0862. Min Act: -0.0000

Data Index: 799526 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9634. Min Act: -0.0000

Data Index: 605568 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1900647 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1545796 (The Pile)

Max Activating Token Index: 858

Text #6

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8840. Min Act: -0.0000

Data Index: 697417 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1026611 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8164. Min Act: -0.0000

Data Index: 1806709 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8184. Min Act: -0.0000

Data Index: 680219 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8055. Min Act: -0.0000

Data Index: 1393623 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.7603. Min Act: -0.0000

Data Index: 340754 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8198. Min Act: -0.0000

Data Index: 1487617 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1621769 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1848241 (The Pile)

Max Activating Token Index: 729

Text #15

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1587034 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.4496. Min Act: -0.0000

Data Index: 712125 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1950484 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.7347. Min Act: -0.0000

Data Index: 562395 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 1.5626. Min Range: -1.5626

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1961217 (The Pile)

Max Activating Token Index: 783