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

Dataset: The Pile

Neuron 2620 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: 1.3677. Min Range: -1.3677

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1923480 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1391768 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1011302 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.3039. Min Act: -0.0000

Data Index: 751508 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1995381 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1617972 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.2308. Min Act: -0.0000

Data Index: 573178 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1737. Min Act: -0.0000

Data Index: 528600 (The Pile)

Max Activating Token Index: 902

Text #8

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1610. Min Act: -0.0000

Data Index: 609602 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1143270 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1775993 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1046. Min Act: -0.0000

Data Index: 915198 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1663917 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1125372 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.2317. Min Act: -0.0000

Data Index: 1759299 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1226. Min Act: -0.0000

Data Index: 1778302 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1424787 (The Pile)

Max Activating Token Index: 227

Text #17

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1167. Min Act: -0.0000

Data Index: 964294 (The Pile)

Max Activating Token Index: 557

Text #18

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.1139. Min Act: -0.0000

Data Index: 816878 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 1.3677. Min Range: -1.3677

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1612123 (The Pile)

Max Activating Token Index: 704