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

Dataset: The Pile

Neuron 3015 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: 0.3918. Min Range: -0.3918

Max Act: 0.3918. Min Act: -0.0000

Data Index: 664679 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1823133 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3237. Min Act: -0.0000

Data Index: 328219 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3126. Min Act: -0.0000

Data Index: 725525 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1282511 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1774802 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2970. Min Act: -0.0000

Data Index: 791600 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2946. Min Act: -0.0000

Data Index: 833334 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2813. Min Act: -0.0000

Data Index: 747171 (The Pile)

Max Activating Token Index: 577

Text #9

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1510410 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1953489 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1398804 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2819. Min Act: -0.0000

Data Index: 531042 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1116653 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2793. Min Act: -0.0000

Data Index: 209414 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2716. Min Act: -0.0000

Data Index: 897690 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1720769 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2792. Min Act: -0.0000

Data Index: 53763 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2699. Min Act: -0.0000

Data Index: 135154 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.3918. Min Range: -0.3918

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1922935 (The Pile)

Max Activating Token Index: 511