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

Dataset: The Pile

Neuron 478 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: 0.9668. Min Range: -0.9668

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1463915 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1912931 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9152. Min Act: -0.0000

Data Index: 885504 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8389. Min Act: -0.0000

Data Index: 308603 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8848. Min Act: -0.0000

Data Index: 597431 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8611. Min Act: -0.0000

Data Index: 412674 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8899. Min Act: -0.0000

Data Index: 155561 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1172398 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1058588 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1217960 (The Pile)

Max Activating Token Index: 397

Text #10

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8611. Min Act: -0.0000

Data Index: 1192894 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1784522 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8839. Min Act: -0.0000

Data Index: 939340 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1813481 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8692. Min Act: -0.0000

Data Index: 281473 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8101. Min Act: -0.0000

Data Index: 868751 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1671924 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1480682 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1009716 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 0.9668. Min Range: -0.9668

Max Act: 0.8904. Min Act: -0.0000

Data Index: 572811 (The Pile)

Max Activating Token Index: 500