Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2709 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1733191 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1792461 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3120. Min Act: -0.0001

Data Index: 945164 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3213. Min Act: -0.0000

Data Index: 899626 (The Pile)

Max Activating Token Index: 125

Text #4

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3104. Min Act: -0.0000

Data Index: 1330746 (The Pile)

Max Activating Token Index: 95

Text #5

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2992. Min Act: -0.0000

Data Index: 996775 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1275877 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2887. Min Act: -0.0000

Data Index: 598059 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1681574 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2876. Min Act: -0.0000

Data Index: 103466 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2772. Min Act: -0.0000

Data Index: 563988 (The Pile)

Max Activating Token Index: 548

Text #11

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1152582 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2769. Min Act: -0.0000

Data Index: 783925 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2769. Min Act: -0.0000

Data Index: 51643 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1630229 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2736. Min Act: -0.0000

Data Index: 859187 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1559527 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1378486 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2691. Min Act: -0.0000

Data Index: 828342 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1828705 (The Pile)

Max Activating Token Index: 193