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

Dataset: The Pile

Neuron 2761 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: 0.5589. Min Range: -0.5589

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1075842 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4846. Min Act: -0.0000

Data Index: 113072 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4068. Min Act: -0.0000

Data Index: 353084 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1065441 (The Pile)

Max Activating Token Index: 1016

Text #4

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3497. Min Act: -0.0000

Data Index: 190170 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1648692 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1256510 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1661776 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1910769 (The Pile)

Max Activating Token Index: 944

Text #9

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3035. Min Act: -0.0000

Data Index: 635566 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3060. Min Act: -0.0000

Data Index: 789764 (The Pile)

Max Activating Token Index: 356

Text #11

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3242. Min Act: -0.0000

Data Index: 70885 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1252614 (The Pile)

Max Activating Token Index: 871

Text #13

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2934. Min Act: 0.0000

Data Index: 126841 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3068. Min Act: -0.0000

Data Index: 561504 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3035. Min Act: -0.0000

Data Index: 1025684 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1665697 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1621789 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2627. Min Act: -0.0000

Data Index: 386451 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2997. Min Act: -0.0000

Data Index: 1584013 (The Pile)

Max Activating Token Index: 591