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

Dataset: The Pile

Neuron 3792 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: 0.5902. Min Range: -0.5902

Max Act: 0.5902. Min Act: -0.0000

Data Index: 298172 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4415. Min Act: -0.0000

Data Index: 828328 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1879869 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4148. Min Act: -0.0000

Data Index: 563657 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1038845 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1288030 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1603764 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3710. Min Act: -0.0000

Data Index: 483948 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3603. Min Act: -0.0000

Data Index: 999852 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1865360 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3678. Min Act: -0.0000

Data Index: 4207 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1083658 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3417. Min Act: -0.0000

Data Index: 702757 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3425. Min Act: -0.0000

Data Index: 855498 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1900129 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1032482 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1626919 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1316883 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1181882 (The Pile)

Max Activating Token Index: 975

Text #19

Max Range: 0.5902. Min Range: -0.5902

Max Act: 0.3358. Min Act: -0.0000

Data Index: 248116 (The Pile)

Max Activating Token Index: 487