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

Dataset: The Pile

Neuron 1839 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: 1.6937. Min Range: -1.6937

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1734468 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.6715. Min Act: -0.0000

Data Index: 122213 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1987814 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1159936 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2603. Min Act: -0.0000

Data Index: 1394091 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2680. Min Act: -0.0000

Data Index: 1134364 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.4096. Min Act: -0.0000

Data Index: 758959 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1123130 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0890. Min Act: -0.0000

Data Index: 936133 (The Pile)

Max Activating Token Index: 989

Text #9

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0896. Min Act: -0.0000

Data Index: 882659 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1367. Min Act: -0.0000

Data Index: 1241009 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2039. Min Act: -0.0000

Data Index: 411062 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1337750 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.3160. Min Act: -0.0000

Data Index: 1799701 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0942. Min Act: -0.0000

Data Index: 1896066 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1354056 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.0725. Min Act: -0.0000

Data Index: 1339094 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1243. Min Act: -0.0000

Data Index: 874206 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.1010. Min Act: -0.0000

Data Index: 641393 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 1.6937. Min Range: -1.6937

Max Act: 1.2564. Min Act: -0.0000

Data Index: 82184 (The Pile)

Max Activating Token Index: 539