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

Dataset: The Pile

Neuron 4861 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1684670 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1452285 (The Pile)

Max Activating Token Index: 812

Text #2

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1788678 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3528. Min Act: -0.0000

Data Index: 435192 (The Pile)

Max Activating Token Index: 827

Text #4

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1874497 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2849. Min Act: -0.0000

Data Index: 217770 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3209. Min Act: -0.0000

Data Index: 328686 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1296419 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2799. Min Act: -0.0000

Data Index: 591625 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2834. Min Act: -0.0000

Data Index: 32404 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2913. Min Act: -0.0000

Data Index: 572329 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2811. Min Act: -0.0000

Data Index: 497345 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3184. Min Act: -0.0000

Data Index: 287825 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2787. Min Act: -0.0000

Data Index: 475496 (The Pile)

Max Activating Token Index: 504

Text #14

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2593. Min Act: -0.0000

Data Index: 817484 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1326256 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2399. Min Act: -0.0000

Data Index: 93273 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2823. Min Act: -0.0000

Data Index: 660807 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1905342 (The Pile)

Max Activating Token Index: 124

Text #19

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1626388 (The Pile)

Max Activating Token Index: 580