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

Dataset: The Pile

Neuron 2138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.8459. Min Act: -0.0000

Data Index: 98110 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.5186. Min Act: -0.0000

Data Index: 506288 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.6062. Min Act: -0.0000

Data Index: 1824958 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.5687. Min Act: -0.0000

Data Index: 908044 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.4810. Min Act: -0.0000

Data Index: 551058 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.4704. Min Act: -0.0000

Data Index: 1204833 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.3025. Min Act: -0.0000

Data Index: 372888 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.2210. Min Act: -0.0000

Data Index: 1604273 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.1987. Min Act: -0.0000

Data Index: 1234909 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.3445. Min Act: -0.0000

Data Index: 1966982 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.1739. Min Act: -0.0000

Data Index: 1185859 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.4336. Min Act: -0.0000

Data Index: 1663022 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.0385. Min Act: -0.0000

Data Index: 1750749 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.0451. Min Act: -0.0000

Data Index: 377350 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.1827. Min Act: -0.0000

Data Index: 1652268 (The Pile)

Max Activating Token Index: 429

Text #15

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.0034. Min Act: -0.0000

Data Index: 1569661 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 3.8459. Min Range: -3.8459

Max Act: 3.1151. Min Act: -0.0000

Data Index: 677688 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 3.8459. Min Range: -3.8459

Max Act: 2.7918. Min Act: -0.0000

Data Index: 435006 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 3.8459. Min Range: -3.8459

Max Act: 2.7668. Min Act: -0.0000

Data Index: 24850 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 3.8459. Min Range: -3.8459

Max Act: 2.8978. Min Act: -0.0000

Data Index: 1856178 (The Pile)

Max Activating Token Index: 470