Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 721 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0915. Min Act: -0.0003

Data Index: 293799 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1547210 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0955. Min Act: -0.0003

Data Index: 96970 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0808. Min Act: -0.0003

Data Index: 956717 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1367765 (The Pile)

Max Activating Token Index: 178

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0856. Min Act: -0.0003

Data Index: 958517 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1129857 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0809. Min Act: -0.0003

Data Index: 29856 (The Pile)

Max Activating Token Index: 899

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0799. Min Act: -0.0003

Data Index: 956603 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0796. Min Act: -0.0003

Data Index: 177647 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0793. Min Act: -0.0003

Data Index: 1108718 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0789. Min Act: -0.0003

Data Index: 1087403 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0814. Min Act: -0.0003

Data Index: 97844 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1153562 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0762. Min Act: -0.0003

Data Index: 785402 (The Pile)

Max Activating Token Index: 939

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1354909 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1933161 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1635960 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0716. Min Act: -0.0003

Data Index: 907614 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0736. Min Act: -0.0003

Data Index: 362552 (The Pile)

Max Activating Token Index: 895