Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 726 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 724722 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1726962 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 69397 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0000

Data Index: 238685 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1782441 (The Pile)

Max Activating Token Index: 1

Text #5

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1485415 (The Pile)

Max Activating Token Index: 1

Text #6

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 118941 (The Pile)

Max Activating Token Index: 1

Text #7

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 54602 (The Pile)

Max Activating Token Index: 1

Text #8

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1266221 (The Pile)

Max Activating Token Index: 1

Text #9

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 720872 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 178685 (The Pile)

Max Activating Token Index: 1

Text #11

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1574756 (The Pile)

Max Activating Token Index: 1

Text #12

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1782373 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 691058 (The Pile)

Max Activating Token Index: 1

Text #14

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1664247 (The Pile)

Max Activating Token Index: 1

Text #15

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1024217 (The Pile)

Max Activating Token Index: 1

Text #16

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1173436 (The Pile)

Max Activating Token Index: 1

Text #17

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1553164 (The Pile)

Max Activating Token Index: 1

Text #18

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1947781 (The Pile)

Max Activating Token Index: 1

Text #19

Max Range: -0.0000. Min Range: 0.0000

Max Act: -0.0000. Min Act: -0.0001

Data Index: 1569784 (The Pile)

Max Activating Token Index: 1