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

Dataset: The Pile

Neuron 2749 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1240275 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1060665 (The Pile)

Max Activating Token Index: 985

Text #2

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8141. Min Act: -0.0000

Data Index: 21301 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6840. Min Act: -0.0000

Data Index: 631048 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1276886 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6880. Min Act: -0.0000

Data Index: 750744 (The Pile)

Max Activating Token Index: 130

Text #6

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1684376 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1462507 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6899. Min Act: -0.0000

Data Index: 860647 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1446119 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6648. Min Act: -0.0000

Data Index: 51717 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7028. Min Act: -0.0000

Data Index: 227452 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1315059 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1891837 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6730. Min Act: -0.0000

Data Index: 781492 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6661. Min Act: -0.0000

Data Index: 514482 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1914098 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1541911 (The Pile)

Max Activating Token Index: 109

Text #18

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1330788 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6614. Min Act: -0.0000

Data Index: 656946 (The Pile)

Max Activating Token Index: 981