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

Dataset: The Pile

Neuron 118 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: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0000

Data Index: 769731 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1880110 (The Pile)

Max Activating Token Index: 991

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1148622 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1378887 (The Pile)

Max Activating Token Index: 848

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0977. Min Act: -0.0000

Data Index: 144543 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1640491 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0965. Min Act: -0.0000

Data Index: 183936 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1454259 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0968. Min Act: -0.0000

Data Index: 55100 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0954. Min Act: 0.0000

Data Index: 927489 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1808100 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0949. Min Act: -0.0000

Data Index: 510279 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0944. Min Act: -0.0000

Data Index: 469913 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0943. Min Act: 0.0000

Data Index: 1682783 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1774330 (The Pile)

Max Activating Token Index: 61

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0933. Min Act: -0.0000

Data Index: 896082 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1643197 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1581909 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0919. Min Act: -0.0000

Data Index: 717636 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0920. Min Act: -0.0000

Data Index: 176077 (The Pile)

Max Activating Token Index: 689