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

Dataset: The Pile

Neuron 4038 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0971. Min Act: -0.0000

Data Index: 710043 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1082979 (The Pile)

Max Activating Token Index: 346

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0973. Min Act: -0.0000

Data Index: 149952 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0943. Min Act: -0.0000

Data Index: 783745 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0922. Min Act: -0.0000

Data Index: 991308 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1813169 (The Pile)

Max Activating Token Index: 114

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1964848 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1749511 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0864. Min Act: -0.0000

Data Index: 968040 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0901. Min Act: -0.0000

Data Index: 919618 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1296175 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1777691 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0875. Min Act: -0.0000

Data Index: 23480 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0846. Min Act: -0.0000

Data Index: 698937 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0871. Min Act: -0.0000

Data Index: 370564 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0907. Min Act: -0.0000

Data Index: 1590627 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1182916 (The Pile)

Max Activating Token Index: 84

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1311218 (The Pile)

Max Activating Token Index: 145

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0856. Min Act: -0.0000

Data Index: 651921 (The Pile)

Max Activating Token Index: 211

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1638568 (The Pile)

Max Activating Token Index: 975