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

Dataset: The Pile

Neuron 58 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1490. Min Act: -0.0000

Data Index: 989055 (The Pile)

Max Activating Token Index: 341

Text #1

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1041838 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1188. Min Act: -0.0000

Data Index: 109248 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1091. Min Act: -0.0000

Data Index: 623389 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1119. Min Act: -0.0000

Data Index: 15158 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1112. Min Act: -0.0000

Data Index: 791306 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1065. Min Act: -0.0000

Data Index: 826012 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1068. Min Act: -0.0000

Data Index: 121367 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0980. Min Act: -0.0000

Data Index: 986630 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1839161 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1038. Min Act: -0.0000

Data Index: 662418 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1755011 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1350110 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1571002 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0895. Min Act: -0.0000

Data Index: 332041 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0989. Min Act: -0.0000

Data Index: 751256 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0946. Min Act: -0.0000

Data Index: 453643 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1085617 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0913. Min Act: -0.0000

Data Index: 151832 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.1490. Min Range: -0.1490

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1995462 (The Pile)

Max Activating Token Index: 554