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

Dataset: The Pile

Neuron 4146 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: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 2534 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 6664 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1368 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 8523 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 7561 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 2129 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 3883 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 8344 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 3818 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 4114 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1520 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 8052 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 7683 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1861 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 7680 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1965 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 5169 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 55 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 631 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0000

Data Index: 4106 (The Pile)

Max Activating Token Index: 1