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

Dataset: The Pile

Neuron 1523 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2666. Min Range: -3.2666

Max Act: 3.2666. Min Act: -0.0000

Data Index: 623711 (The Pile)

Max Activating Token Index: 7

Text #1

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.9280. Min Act: -0.0000

Data Index: 1120319 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 3.2666. Min Range: -3.2666

Max Act: 3.0517. Min Act: -0.0000

Data Index: 1081878 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.7722. Min Act: -0.0000

Data Index: 211660 (The Pile)

Max Activating Token Index: 8

Text #4

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.7510. Min Act: -0.0000

Data Index: 1948573 (The Pile)

Max Activating Token Index: 9

Text #5

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.7390. Min Act: -0.0000

Data Index: 1284762 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.6005. Min Act: -0.0000

Data Index: 1616467 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.9792. Min Act: -0.0000

Data Index: 335708 (The Pile)

Max Activating Token Index: 7

Text #8

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.6991. Min Act: -0.0000

Data Index: 861685 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.7001. Min Act: -0.0000

Data Index: 1545571 (The Pile)

Max Activating Token Index: 134

Text #10

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.6916. Min Act: -0.0000

Data Index: 523822 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.8898. Min Act: -0.0000

Data Index: 430297 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.5945. Min Act: -0.0000

Data Index: 781906 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.8259. Min Act: -0.0000

Data Index: 1454011 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.4240. Min Act: -0.0000

Data Index: 930749 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.6151. Min Act: -0.0000

Data Index: 1590620 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.5753. Min Act: -0.0000

Data Index: 663282 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.5586. Min Act: -0.0000

Data Index: 569839 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.6828. Min Act: -0.0000

Data Index: 53371 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 3.2666. Min Range: -3.2666

Max Act: 2.5359. Min Act: -0.0000

Data Index: 423222 (The Pile)

Max Activating Token Index: 8