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

Dataset: The Pile

Neuron 4018 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.5890. Min Act: -0.0000

Data Index: 847546 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.5041. Min Act: -0.0000

Data Index: 840781 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1566658 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.3418. Min Act: -0.0000

Data Index: 1355404 (The Pile)

Max Activating Token Index: 159

Text #4

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2851. Min Act: -0.0000

Data Index: 189975 (The Pile)

Max Activating Token Index: 686

Text #5

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2197. Min Act: -0.0000

Data Index: 636694 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1516568 (The Pile)

Max Activating Token Index: 413

Text #7

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1238146 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.3699. Min Act: -0.0000

Data Index: 1271428 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2151. Min Act: -0.0000

Data Index: 1601907 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.1891. Min Act: -0.0000

Data Index: 849223 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1194282 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.1565. Min Act: -0.0000

Data Index: 259840 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.0967. Min Act: -0.0000

Data Index: 203203 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2123. Min Act: -0.0000

Data Index: 898936 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.1057. Min Act: -0.0000

Data Index: 781378 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1948965 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2390. Min Act: -0.0000

Data Index: 474099 (The Pile)

Max Activating Token Index: 899

Text #18

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1686797 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 1.5890. Min Range: -1.5890

Max Act: 1.1071. Min Act: -0.0000

Data Index: 677328 (The Pile)

Max Activating Token Index: 850