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

Dataset: The Pile

Neuron 539 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: 0.0000

Data Index: 391744 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0636. Min Act: 0.0000

Data Index: 1378756 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0614. Min Act: 0.0000

Data Index: 232001 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0602. Min Act: 0.0000

Data Index: 227740 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1865283 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0595. Min Act: 0.0000

Data Index: 60234 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0594. Min Act: 0.0000

Data Index: 1744452 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0582. Min Act: 0.0000

Data Index: 429193 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0581. Min Act: 0.0000

Data Index: 1565197 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0599. Min Act: 0.0000

Data Index: 1066029 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1069700 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1528252 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0571. Min Act: 0.0000

Data Index: 1572657 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1743338 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0567. Min Act: 0.0000

Data Index: 527689 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0567. Min Act: 0.0000

Data Index: 717712 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0566. Min Act: 0.0000

Data Index: 221331 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0566. Min Act: 0.0000

Data Index: 73822 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0564. Min Act: -0.0000

Data Index: 468792 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0562. Min Act: -0.0000

Data Index: 75407 (The Pile)

Max Activating Token Index: 46