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

Dataset: The Pile

Neuron 2310 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: 0.3950. Min Range: -0.3950

Max Act: 0.3950. Min Act: -0.0000

Data Index: 1616536 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3428. Min Act: -0.0000

Data Index: 965674 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3063. Min Act: 0.0000

Data Index: 466427 (The Pile)

Max Activating Token Index: 754

Text #3

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1043936 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3104. Min Act: 0.0000

Data Index: 1438346 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1521897 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3164. Min Act: -0.0000

Data Index: 857891 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2867. Min Act: -0.0000

Data Index: 130874 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3001. Min Act: -0.0000

Data Index: 325710 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1915588 (The Pile)

Max Activating Token Index: 712

Text #10

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1129856 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2888. Min Act: -0.0000

Data Index: 972889 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2843. Min Act: -0.0000

Data Index: 39816 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2723. Min Act: 0.0000

Data Index: 1740180 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1481098 (The Pile)

Max Activating Token Index: 939

Text #15

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1194037 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1188352 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2684. Min Act: -0.0000

Data Index: 365356 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1648305 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1374413 (The Pile)

Max Activating Token Index: 540