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

Dataset: The Pile

Neuron 3412 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: 0.9579. Min Range: -0.9579

Max Act: 0.9579. Min Act: -0.0000

Data Index: 910569 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7416. Min Act: -0.0000

Data Index: 683692 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.8074. Min Act: -0.0000

Data Index: 625086 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7820. Min Act: -0.0000

Data Index: 186038 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7580. Min Act: -0.0000

Data Index: 419437 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1448217 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7448. Min Act: -0.0000

Data Index: 1247848 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1519093 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6539. Min Act: -0.0000

Data Index: 997713 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1319020 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1140037 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6811. Min Act: -0.0000

Data Index: 505526 (The Pile)

Max Activating Token Index: 39

Text #12

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6718. Min Act: -0.0000

Data Index: 233048 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6734. Min Act: -0.0000

Data Index: 587659 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6964. Min Act: -0.0000

Data Index: 953534 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6669. Min Act: -0.0000

Data Index: 971013 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1051920 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.7089. Min Act: -0.0000

Data Index: 859133 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6992. Min Act: -0.0000

Data Index: 845283 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.9579. Min Range: -0.9579

Max Act: 0.6557. Min Act: -0.0000

Data Index: 728014 (The Pile)

Max Activating Token Index: 20