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

Dataset: The Pile

Neuron 4374 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: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 10958 (The Pile)

Max Activating Token Index: 1

Text #1

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 3570 (The Pile)

Max Activating Token Index: 1

Text #2

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 12540 (The Pile)

Max Activating Token Index: 1

Text #3

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 5643 (The Pile)

Max Activating Token Index: 1

Text #4

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 5123 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1970 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 4855 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 7478 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1317 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 10004 (The Pile)

Max Activating Token Index: 1

Text #10

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1942 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 8945 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 184 (The Pile)

Max Activating Token Index: 1

Text #13

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 2539 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 3719 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 5951 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 2337 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 10880 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 10061 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: 0.0842. Min Range: -0.0842

Max Act: 0.0842. Min Act: -0.0000

Data Index: 11365 (The Pile)

Max Activating Token Index: 1