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

Dataset: The Pile

Neuron 209 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1409328 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.2701. Min Act: -0.0000

Data Index: 1014510 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1186790 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.1620. Min Act: -0.0000

Data Index: 509273 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1031208 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.2109. Min Act: -0.0000

Data Index: 532838 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0688. Min Act: -0.0000

Data Index: 936068 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.2601. Min Act: -0.0000

Data Index: 1342183 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.1272. Min Act: -0.0000

Data Index: 786815 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0508. Min Act: -0.0000

Data Index: 416101 (The Pile)

Max Activating Token Index: 982

Text #10

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0799. Min Act: -0.0000

Data Index: 281855 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0721. Min Act: -0.0000

Data Index: 1568178 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.1047. Min Act: -0.0000

Data Index: 23469 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1147676 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1688912 (The Pile)

Max Activating Token Index: 129

Text #15

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1597148 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1861725 (The Pile)

Max Activating Token Index: 657

Text #17

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9895. Min Act: -0.0000

Data Index: 92811 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 1.3068. Min Range: -1.3068

Max Act: 0.9507. Min Act: -0.0000

Data Index: 765142 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.3068. Min Range: -1.3068

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1254950 (The Pile)

Max Activating Token Index: 594