Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4452. Min Act: -0.0000

Data Index: 900793 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1821500 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1399900 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3938. Min Act: -0.0000

Data Index: 569391 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1095543 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4008. Min Act: -0.0000

Data Index: 548344 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1968956 (The Pile)

Max Activating Token Index: 686

Text #7

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1437094 (The Pile)

Max Activating Token Index: 496

Text #8

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4073. Min Act: -0.0000

Data Index: 836308 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1573443 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1166366 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1136372 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3880. Min Act: -0.0000

Data Index: 116212 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1691549 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3604. Min Act: -0.0000

Data Index: 5283 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3754. Min Act: -0.0000

Data Index: 726750 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3635. Min Act: -0.0000

Data Index: 275648 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1435749 (The Pile)

Max Activating Token Index: 649

Text #18

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1300722 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 0.4583. Min Range: -0.4583

Max Act: 0.3564. Min Act: 0.0000

Data Index: 1440247 (The Pile)

Max Activating Token Index: 192