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

Dataset: The Pile

Neuron 2111 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: 1.4866. Min Range: -1.4866

Max Act: 1.4866. Min Act: -0.0000

Data Index: 594915 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1151053 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1456097 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.0100. Min Act: -0.0000

Data Index: 203991 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.0600. Min Act: -0.0000

Data Index: 383922 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 1.4866. Min Range: -1.4866

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1294810 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.9596. Min Act: -0.0000

Data Index: 202900 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.9308. Min Act: -0.0000

Data Index: 524519 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8204. Min Act: -0.0000

Data Index: 1504259 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.9701. Min Act: -0.0000

Data Index: 183831 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8715. Min Act: -0.0000

Data Index: 792697 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1867607 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1013971 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8403. Min Act: -0.0000

Data Index: 388676 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.7929. Min Act: -0.0000

Data Index: 73811 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1831057 (The Pile)

Max Activating Token Index: 246

Text #16

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1540553 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8677. Min Act: -0.0000

Data Index: 48752 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8241. Min Act: -0.0000

Data Index: 734120 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 1.4866. Min Range: -1.4866

Max Act: 0.8219. Min Act: -0.0000

Data Index: 334243 (The Pile)

Max Activating Token Index: 32