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

Dataset: The Pile

Neuron 2859 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0970. Min Act: -0.0000

Data Index: 157865 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0947. Min Act: -0.0000

Data Index: 869955 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: 0.0000

Data Index: 1284493 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0935. Min Act: -0.0000

Data Index: 485474 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1089361 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0906. Min Act: -0.0000

Data Index: 1713370 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0817. Min Act: -0.0000

Data Index: 540185 (The Pile)

Max Activating Token Index: 976

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0807. Min Act: -0.0000

Data Index: 383605 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0829. Min Act: -0.0000

Data Index: 422389 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0807. Min Act: 0.0000

Data Index: 386560 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1678424 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1211835 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1970991 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1877061 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0714. Min Act: -0.0000

Data Index: 993720 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0723. Min Act: -0.0000

Data Index: 549650 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0749. Min Act: -0.0000

Data Index: 652162 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1820117 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0722. Min Act: 0.0000

Data Index: 1818425 (The Pile)

Max Activating Token Index: 795

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1294110 (The Pile)

Max Activating Token Index: 731