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

Dataset: The Pile

Neuron 1250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1697696 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5058. Min Act: -0.0000

Data Index: 711536 (The Pile)

Max Activating Token Index: 991

Text #2

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1309815 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.5133. Min Act: -0.0000

Data Index: 904152 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4465. Min Act: -0.0000

Data Index: 361400 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4457. Min Act: -0.0000

Data Index: 593815 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4127. Min Act: -0.0000

Data Index: 341514 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4360. Min Act: -0.0000

Data Index: 653935 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4197. Min Act: -0.0000

Data Index: 1867599 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3962. Min Act: -0.0000

Data Index: 467285 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4007. Min Act: -0.0000

Data Index: 448032 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4005. Min Act: -0.0000

Data Index: 519060 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4254. Min Act: -0.0000

Data Index: 413533 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1071778 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3941. Min Act: -0.0000

Data Index: 978781 (The Pile)

Max Activating Token Index: 932

Text #15

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3826. Min Act: -0.0000

Data Index: 209249 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1732938 (The Pile)

Max Activating Token Index: 778

Text #17

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3772. Min Act: -0.0000

Data Index: 733737 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1254085 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 0.6545. Min Range: -0.6545

Max Act: 0.3534. Min Act: -0.0000

Data Index: 871195 (The Pile)

Max Activating Token Index: 884