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

Dataset: The Pile

Neuron 2189 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5722. Min Act: -0.0000

Data Index: 1864847 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5553. Min Act: -0.0000

Data Index: 11865 (The Pile)

Max Activating Token Index: 963

Text #2

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4621. Min Act: -0.0000

Data Index: 437566 (The Pile)

Max Activating Token Index: 630

Text #3

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1102771 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1739724 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4178. Min Act: -0.0000

Data Index: 630085 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1354971 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4357. Min Act: -0.0000

Data Index: 948905 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3886. Min Act: -0.0000

Data Index: 693509 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3952. Min Act: -0.0000

Data Index: 399174 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3869. Min Act: -0.0000

Data Index: 152518 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3891. Min Act: -0.0000

Data Index: 320166 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3713. Min Act: 0.0000

Data Index: 1679573 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3739. Min Act: -0.0000

Data Index: 566378 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1389423 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3818. Min Act: -0.0000

Data Index: 141156 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3907. Min Act: -0.0000

Data Index: 158087 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1708590 (The Pile)

Max Activating Token Index: 39

Text #18

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3552. Min Act: -0.0000

Data Index: 474985 (The Pile)

Max Activating Token Index: 659

Text #19

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3906. Min Act: -0.0000

Data Index: 616610 (The Pile)

Max Activating Token Index: 74