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

Dataset: The Pile

Neuron 4161 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: 0.0828. Min Range: -0.0828

Max Act: 0.0816. Min Act: -0.0000

Data Index: 129597 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0828. Min Act: -0.0000

Data Index: 943091 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0751. Min Act: -0.0000

Data Index: 166824 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1336762 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1730861 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1083295 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1652199 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0599. Min Act: -0.0000

Data Index: 985894 (The Pile)

Max Activating Token Index: 721

Text #8

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0574. Min Act: -0.0000

Data Index: 981567 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0609. Min Act: -0.0000

Data Index: 993094 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1200796 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0605. Min Act: -0.0000

Data Index: 1465218 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0598. Min Act: -0.0000

Data Index: 937397 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1695166 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0581. Min Act: -0.0000

Data Index: 129759 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1994075 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0550. Min Act: -0.0000

Data Index: 339327 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1878329 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0653. Min Act: -0.0000

Data Index: 1323739 (The Pile)

Max Activating Token Index: 664

Text #19

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0632. Min Act: -0.0000

Data Index: 709272 (The Pile)

Max Activating Token Index: 604