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

Dataset: The Pile

Neuron 525 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: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1634501 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0000

Data Index: 458634 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0000

Data Index: 286504 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1683446 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1292479 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1213599 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1216393 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 153118 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1571417 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 202896 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 18524 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 995650 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 741624 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0306. Min Act: -0.0000

Data Index: 22715 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0288. Min Act: -0.0000

Data Index: 639356 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0288. Min Act: -0.0000

Data Index: 329355 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0288. Min Act: -0.0000

Data Index: 640098 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0288. Min Act: -0.0000

Data Index: 389596 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0288. Min Act: -0.0000

Data Index: 640719 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0528. Min Range: -0.0528

Max Act: 0.0288. Min Act: -0.0000

Data Index: 457008 (The Pile)

Max Activating Token Index: 1