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

Dataset: The Pile

Neuron 3277 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: 1.1030. Min Range: -1.1030

Max Act: 1.1030. Min Act: -0.0000

Data Index: 562564 (The Pile)

Max Activating Token Index: 615

Text #1

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1642034 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1831098 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1948530 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8348. Min Act: -0.0000

Data Index: 735372 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8660. Min Act: -0.0000

Data Index: 5631 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8145. Min Act: -0.0000

Data Index: 721500 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8353. Min Act: -0.0000

Data Index: 1058731 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8272. Min Act: -0.0000

Data Index: 211673 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7761. Min Act: -0.0000

Data Index: 211363 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7345. Min Act: -0.0000

Data Index: 1318032 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7358. Min Act: -0.0000

Data Index: 864193 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1108718 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8057. Min Act: -0.0000

Data Index: 1869694 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7725. Min Act: -0.0000

Data Index: 614029 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1580384 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7629. Min Act: -0.0000

Data Index: 673972 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7617. Min Act: -0.0000

Data Index: 159040 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7863. Min Act: -0.0000

Data Index: 52720 (The Pile)

Max Activating Token Index: 755

Text #19

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7422. Min Act: -0.0000

Data Index: 842914 (The Pile)

Max Activating Token Index: 110