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

Dataset: The Pile

Neuron 1579 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: 0.6924. Min Range: -0.6924

Max Act: 0.6924. Min Act: -0.0000

Data Index: 81673 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1276605 (The Pile)

Max Activating Token Index: 766

Text #2

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1096168 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6067. Min Act: -0.0000

Data Index: 269741 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6028. Min Act: -0.0000

Data Index: 789930 (The Pile)

Max Activating Token Index: 532

Text #5

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6218. Min Act: -0.0000

Data Index: 97973 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1979726 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5386. Min Act: -0.0000

Data Index: 918939 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6351. Min Act: -0.0000

Data Index: 739348 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.4906. Min Act: -0.0000

Data Index: 899106 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1516203 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1596029 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1646091 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.6098. Min Act: -0.0000

Data Index: 381684 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1458055 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5100. Min Act: -0.0000

Data Index: 965796 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1285970 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5160. Min Act: -0.0000

Data Index: 6215 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1435126 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.6924. Min Range: -0.6924

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1554353 (The Pile)

Max Activating Token Index: 335