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

Dataset: The Pile

Neuron 3449 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 2.1063. Min Range: -2.1063

Max Act: 2.1063. Min Act: -0.0000

Data Index: 1394584 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.7261. Min Act: -0.0000

Data Index: 158889 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1706057 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1149029 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5458. Min Act: -0.0000

Data Index: 853183 (The Pile)

Max Activating Token Index: 819

Text #5

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5377. Min Act: -0.0000

Data Index: 605564 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1764966 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4830. Min Act: -0.0000

Data Index: 437288 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4539. Min Act: -0.0000

Data Index: 439500 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4607. Min Act: -0.0000

Data Index: 848165 (The Pile)

Max Activating Token Index: 122

Text #10

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.4372. Min Act: -0.0000

Data Index: 401868 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3865. Min Act: -0.0000

Data Index: 932154 (The Pile)

Max Activating Token Index: 32

Text #12

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1731940 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3633. Min Act: -0.0000

Data Index: 1542281 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3152. Min Act: -0.0000

Data Index: 431831 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1533027 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.2964. Min Act: -0.0000

Data Index: 124840 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1476224 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1741458 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 2.1063. Min Range: -2.1063

Max Act: 1.2798. Min Act: -0.0000

Data Index: 658603 (The Pile)

Max Activating Token Index: 623