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

Dataset: The Pile

Neuron 4108 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.7182. Min Act: -0.0000

Data Index: 1108515 (The Pile)

Max Activating Token Index: 880

Text #1

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.7064. Min Act: -0.0000

Data Index: 1513048 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.4836. Min Act: -0.0000

Data Index: 106580 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.8887. Min Act: -0.0000

Data Index: 581057 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.3265. Min Act: -0.0000

Data Index: 1707100 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.6342. Min Act: -0.0000

Data Index: 1911802 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.8035. Min Act: -0.0000

Data Index: 1620163 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.1733. Min Act: -0.0000

Data Index: 89864 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.1376. Min Act: -0.0000

Data Index: 1430125 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.2022. Min Act: -0.0000

Data Index: 457695 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.1794. Min Act: -0.0000

Data Index: 1944936 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.1506. Min Act: -0.0000

Data Index: 420470 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.9803. Min Act: -0.0000

Data Index: 1820907 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.1123. Min Act: -0.0000

Data Index: 1580152 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.2596. Min Act: -0.0000

Data Index: 1781302 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0698. Min Act: -0.0000

Data Index: 675708 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.8066. Min Act: -0.0000

Data Index: 466701 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 3.8887. Min Range: -3.8887

Max Act: 3.0584. Min Act: -0.0000

Data Index: 948737 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.9088. Min Act: -0.0000

Data Index: 1322401 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 3.8887. Min Range: -3.8887

Max Act: 2.8687. Min Act: -0.0000

Data Index: 265060 (The Pile)

Max Activating Token Index: 145