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

Dataset: The Pile

Neuron 4019 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: 0.8875. Min Range: -0.8875

Max Act: 0.8875. Min Act: -0.0000

Data Index: 716537 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.8601. Min Act: -0.0000

Data Index: 1484890 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1101945 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7164. Min Act: -0.0000

Data Index: 353994 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7198. Min Act: -0.0000

Data Index: 1496054 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7777. Min Act: -0.0000

Data Index: 625384 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1314987 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7406. Min Act: -0.0000

Data Index: 93100 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1762506 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1120143 (The Pile)

Max Activating Token Index: 945

Text #10

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1020569 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6807. Min Act: -0.0000

Data Index: 102640 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6756. Min Act: -0.0000

Data Index: 105101 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6256. Min Act: -0.0000

Data Index: 661699 (The Pile)

Max Activating Token Index: 713

Text #14

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1816283 (The Pile)

Max Activating Token Index: 400

Text #15

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6799. Min Act: -0.0000

Data Index: 874842 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1779882 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6865. Min Act: -0.0000

Data Index: 252893 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1690362 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.8875. Min Range: -0.8875

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1056983 (The Pile)

Max Activating Token Index: 995