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

Dataset: The Pile

Neuron 2088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7756. Min Act: -0.0000

Data Index: 786645 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7508. Min Act: -0.0000

Data Index: 839847 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1970689 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1318111 (The Pile)

Max Activating Token Index: 106

Text #4

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1652723 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1081984 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5778. Min Act: -0.0000

Data Index: 201041 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7829. Min Act: -0.0000

Data Index: 299703 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6628. Min Act: -0.0000

Data Index: 163318 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1404393 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1667134 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1788874 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1791555 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5758. Min Act: -0.0000

Data Index: 979135 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6203. Min Act: -0.0000

Data Index: 668151 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1690782 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1684514 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6632. Min Act: -0.0000

Data Index: 410818 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1711442 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6212. Min Act: -0.0001

Data Index: 1449312 (The Pile)

Max Activating Token Index: 829