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

Dataset: The Pile

Neuron 3051 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1756082 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1657972 (The Pile)

Max Activating Token Index: 48

Text #2

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4157. Min Act: -0.0000

Data Index: 561610 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1577488 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3614. Min Act: -0.0000

Data Index: 952430 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3718. Min Act: -0.0000

Data Index: 132180 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1014698 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1385746 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1138626 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3424. Min Act: -0.0000

Data Index: 1184685 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1056334 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3556. Min Act: -0.0000

Data Index: 577227 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3257. Min Act: -0.0000

Data Index: 961425 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3257. Min Act: -0.0000

Data Index: 111652 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1587911 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3432. Min Act: -0.0000

Data Index: 759575 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3412. Min Act: -0.0000

Data Index: 190233 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1798134 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3164. Min Act: -0.0000

Data Index: 384398 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.4640. Min Range: -0.4640

Max Act: 0.3184. Min Act: -0.0000

Data Index: 934196 (The Pile)

Max Activating Token Index: 120