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

Dataset: The Pile

Neuron 3102 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: 1.6909. Min Range: -1.6909

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1988442 (The Pile)

Max Activating Token Index: 947

Text #1

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.4451. Min Act: -0.0000

Data Index: 1771268 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.2555. Min Act: -0.0000

Data Index: 948793 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1795179 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.2610. Min Act: -0.0000

Data Index: 536195 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1388973 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1322633 (The Pile)

Max Activating Token Index: 286

Text #7

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.1370. Min Act: -0.0000

Data Index: 500556 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1565942 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.1641. Min Act: -0.0000

Data Index: 1006884 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1174383 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.0780. Min Act: -0.0000

Data Index: 638213 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1626525 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 1.6909. Min Range: -1.6909

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1229548 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 1.6909. Min Range: -1.6909

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1183927 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 1.6909. Min Range: -1.6909

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1374659 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 1.6909. Min Range: -1.6909

Max Act: 0.9264. Min Act: -0.0000

Data Index: 51351 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 1.6909. Min Range: -1.6909

Max Act: 0.9167. Min Act: -0.0000

Data Index: 282345 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 1.6909. Min Range: -1.6909

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1530237 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 1.6909. Min Range: -1.6909

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1196376 (The Pile)

Max Activating Token Index: 563