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

Dataset: The Pile

Neuron 1929 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: 0.8668. Min Range: -0.8668

Max Act: 0.8668. Min Act: -0.0000

Data Index: 1005979 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7608. Min Act: -0.0000

Data Index: 165476 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.7156. Min Act: -0.0000

Data Index: 383698 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6890. Min Act: -0.0000

Data Index: 464217 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1005208 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6708. Min Act: -0.0000

Data Index: 903538 (The Pile)

Max Activating Token Index: 128

Text #6

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1193542 (The Pile)

Max Activating Token Index: 839

Text #7

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5878. Min Act: -0.0000

Data Index: 594398 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1844974 (The Pile)

Max Activating Token Index: 104

Text #9

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6394. Min Act: -0.0000

Data Index: 601451 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1542987 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1442618 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1004699 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6115. Min Act: -0.0000

Data Index: 770135 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1946561 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1779117 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5961. Min Act: -0.0000

Data Index: 211137 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1105874 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1183440 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 0.8668. Min Range: -0.8668

Max Act: 0.6269. Min Act: -0.0000

Data Index: 294941 (The Pile)

Max Activating Token Index: 84