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

Dataset: The Pile

Neuron 4578 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: 0.5417. Min Range: -0.5417

Max Act: 0.5417. Min Act: -0.0000

Data Index: 558466 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4856. Min Act: -0.0000

Data Index: 849434 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4982. Min Act: -0.0000

Data Index: 190667 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1091663 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3664. Min Act: -0.0000

Data Index: 218039 (The Pile)

Max Activating Token Index: 955

Text #5

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4511. Min Act: -0.0000

Data Index: 569724 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1850865 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3612. Min Act: -0.0000

Data Index: 293773 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1738981 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.4026. Min Act: -0.0000

Data Index: 330138 (The Pile)

Max Activating Token Index: 863

Text #10

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3447. Min Act: -0.0000

Data Index: 672714 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3297. Min Act: -0.0000

Data Index: 416252 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1814668 (The Pile)

Max Activating Token Index: 846

Text #13

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2972. Min Act: -0.0000

Data Index: 609402 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1988882 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1172239 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2939. Min Act: -0.0000

Data Index: 265768 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2981. Min Act: -0.0000

Data Index: 785343 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1601562 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 0.5417. Min Range: -0.5417

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1823891 (The Pile)

Max Activating Token Index: 746