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

Dataset: The Pile

Neuron 3283 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1674292 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.8017. Min Act: -0.0000

Data Index: 777176 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1140402 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1684659 (The Pile)

Max Activating Token Index: 201

Text #4

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1793141 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.7540. Min Act: -0.0000

Data Index: 153231 (The Pile)

Max Activating Token Index: 923

Text #6

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6856. Min Act: -0.0000

Data Index: 466619 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1496793 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1343580 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1955503 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6324. Min Act: -0.0000

Data Index: 764017 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5940. Min Act: -0.0000

Data Index: 259528 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6195. Min Act: -0.0000

Data Index: 354802 (The Pile)

Max Activating Token Index: 915

Text #13

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6568. Min Act: -0.0000

Data Index: 838826 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6055. Min Act: -0.0000

Data Index: 97867 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1313602 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6207. Min Act: -0.0000

Data Index: 700701 (The Pile)

Max Activating Token Index: 803

Text #17

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1959633 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6462. Min Act: -0.0000

Data Index: 915277 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5665. Min Act: -0.0000

Data Index: 864748 (The Pile)

Max Activating Token Index: 953