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

Dataset: The Pile

Neuron 3045 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: 0.3931. Min Range: -0.3931

Max Act: 0.3931. Min Act: -0.0000

Data Index: 77417 (The Pile)

Max Activating Token Index: 812

Text #1

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3546. Min Act: -0.0000

Data Index: 1277987 (The Pile)

Max Activating Token Index: 369

Text #2

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1796400 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3109. Min Act: -0.0000

Data Index: 414954 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3188. Min Act: -0.0000

Data Index: 806051 (The Pile)

Max Activating Token Index: 364

Text #5

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1861536 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1920848 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1007236 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1965126 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1348552 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2831. Min Act: -0.0000

Data Index: 614917 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2805. Min Act: -0.0000

Data Index: 443998 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2827. Min Act: -0.0000

Data Index: 1551589 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1481437 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2660. Min Act: -0.0000

Data Index: 131728 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1893450 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2648. Min Act: -0.0000

Data Index: 6704 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2724. Min Act: -0.0000

Data Index: 471924 (The Pile)

Max Activating Token Index: 742

Text #18

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1248863 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 0.3931. Min Range: -0.3931

Max Act: 0.2694. Min Act: -0.0000

Data Index: 775511 (The Pile)

Max Activating Token Index: 957