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

Dataset: The Pile

Neuron 3771 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1885181 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.4421. Min Act: -0.0000

Data Index: 902121 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1256399 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1910432 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1563949 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1251005 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1390663 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1578159 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3687. Min Act: -0.0000

Data Index: 594437 (The Pile)

Max Activating Token Index: 323

Text #9

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1371867 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3510. Min Act: -0.0000

Data Index: 680231 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1900438 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3098. Min Act: -0.0000

Data Index: 475971 (The Pile)

Max Activating Token Index: 450

Text #13

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3065. Min Act: -0.0000

Data Index: 225112 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1003715 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.2787. Min Act: -0.0000

Data Index: 26367 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.2831. Min Act: -0.0000

Data Index: 920455 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.2737. Min Act: -0.0000

Data Index: 907660 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.2999. Min Act: -0.0000

Data Index: 1828785 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 0.8146. Min Range: -0.8146

Max Act: 0.2759. Min Act: -0.0000

Data Index: 414319 (The Pile)

Max Activating Token Index: 103