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

Dataset: The Pile

Neuron 339 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1169107 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.7016. Min Act: -0.0000

Data Index: 663840 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6467. Min Act: -0.0000

Data Index: 826785 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1771348 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6549. Min Act: -0.0000

Data Index: 909342 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5978. Min Act: -0.0000

Data Index: 910529 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1916564 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1725413 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1423467 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1871882 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1050970 (The Pile)

Max Activating Token Index: 631

Text #11

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1847946 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1938722 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1348937 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1842247 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1466791 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6092. Min Act: -0.0000

Data Index: 318642 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1187763 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5520. Min Act: -0.0000

Data Index: 203603 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5785. Min Act: -0.0000

Data Index: 191839 (The Pile)

Max Activating Token Index: 285