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

Dataset: The Pile

Neuron 2023 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0000

Data Index: 768765 (The Pile)

Max Activating Token Index: 5

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0772. Min Act: -0.0000

Data Index: 788466 (The Pile)

Max Activating Token Index: 10

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0770. Min Act: 0.0000

Data Index: 237842 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1433757 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 597520 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1938934 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1214899 (The Pile)

Max Activating Token Index: 2

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 74892 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 575858 (The Pile)

Max Activating Token Index: 2

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 170562 (The Pile)

Max Activating Token Index: 2

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1357034 (The Pile)

Max Activating Token Index: 2

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1269785 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0760. Min Act: -0.0000

Data Index: 657413 (The Pile)

Max Activating Token Index: 2

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1163337 (The Pile)

Max Activating Token Index: 4

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1788053 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1769212 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1069938 (The Pile)

Max Activating Token Index: 4

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0751. Min Act: -0.0000

Data Index: 734090 (The Pile)

Max Activating Token Index: 4

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0750. Min Act: -0.0000

Data Index: 798559 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0748. Min Act: -0.0000

Data Index: 937694 (The Pile)

Max Activating Token Index: 21