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

Dataset: The Pile

Neuron 2502 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: 0.6087. Min Range: -0.6087

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1126637 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.6087. Min Act: -0.0000

Data Index: 462664 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1475399 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1674184 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4508. Min Act: 0.0001

Data Index: 1847529 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1522589 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1044799 (The Pile)

Max Activating Token Index: 833

Text #7

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1239362 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.4697. Min Act: -0.0000

Data Index: 509946 (The Pile)

Max Activating Token Index: 954

Text #9

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3995. Min Act: -0.0000

Data Index: 528610 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3783. Min Act: -0.0000

Data Index: 792941 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1564608 (The Pile)

Max Activating Token Index: 884

Text #12

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3496. Min Act: -0.0000

Data Index: 88813 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3175. Min Act: -0.0000

Data Index: 699451 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1419754 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3031. Min Act: -0.0000

Data Index: 20463 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1577159 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3426. Min Act: -0.0000

Data Index: 193114 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3233. Min Act: -0.0000

Data Index: 834853 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 0.6087. Min Range: -0.6087

Max Act: 0.3491. Min Act: -0.0000

Data Index: 550006 (The Pile)

Max Activating Token Index: 11