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

Dataset: The Pile

Neuron 3962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.5676. Min Act: -0.0000

Data Index: 150159 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.5702. Min Act: -0.0000

Data Index: 522512 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1105042 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.4508. Min Act: -0.0000

Data Index: 799736 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.4164. Min Act: -0.0000

Data Index: 1148968 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3946. Min Act: -0.0000

Data Index: 1922582 (The Pile)

Max Activating Token Index: 545

Text #6

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1030279 (The Pile)

Max Activating Token Index: 721

Text #7

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.2905. Min Act: -0.0000

Data Index: 252510 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3827. Min Act: -0.0000

Data Index: 964203 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3589. Min Act: -0.0000

Data Index: 73571 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1560754 (The Pile)

Max Activating Token Index: 449

Text #11

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.4110. Min Act: -0.0000

Data Index: 728964 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3954. Min Act: -0.0000

Data Index: 145405 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1568261 (The Pile)

Max Activating Token Index: 17

Text #14

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3606. Min Act: -0.0000

Data Index: 1895834 (The Pile)

Max Activating Token Index: 888

Text #15

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.3418. Min Act: -0.0000

Data Index: 1428494 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.2064. Min Act: -0.0000

Data Index: 1061110 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1718994 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.2601. Min Act: -0.0000

Data Index: 880032 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 1.5702. Min Range: -1.5702

Max Act: 1.2337. Min Act: -0.0000

Data Index: 152193 (The Pile)

Max Activating Token Index: 584