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

Dataset: The Pile

Neuron 113 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2664. Min Act: -0.0000

Data Index: 730594 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2551. Min Act: -0.0000

Data Index: 539643 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1601875 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2470. Min Act: -0.0000

Data Index: 968714 (The Pile)

Max Activating Token Index: 340

Text #4

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1056954 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1563321 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2333. Min Act: 0.0000

Data Index: 1319651 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1744492 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1083177 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1734574 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1941. Min Act: -0.0000

Data Index: 494585 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1697344 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1827959 (The Pile)

Max Activating Token Index: 855

Text #13

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1984. Min Act: -0.0000

Data Index: 628058 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1373221 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1797. Min Act: -0.0000

Data Index: 202703 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2025. Min Act: -0.0000

Data Index: 56154 (The Pile)

Max Activating Token Index: 485

Text #17

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1182438 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1974. Min Act: -0.0000

Data Index: 1560672 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1871. Min Act: -0.0000

Data Index: 903751 (The Pile)

Max Activating Token Index: 712