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

Dataset: The Pile

Neuron 3705 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: 0.8736. Min Range: -0.8736

Max Act: 0.8736. Min Act: -0.0000

Data Index: 128098 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7908. Min Act: -0.0000

Data Index: 109380 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7675. Min Act: -0.0000

Data Index: 578589 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7807. Min Act: -0.0000

Data Index: 387915 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7620. Min Act: -0.0000

Data Index: 465538 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1199304 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8436. Min Act: -0.0000

Data Index: 573799 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6898. Min Act: -0.0000

Data Index: 307809 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1552312 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1315053 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7045. Min Act: -0.0000

Data Index: 791126 (The Pile)

Max Activating Token Index: 140

Text #11

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1979999 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7112. Min Act: -0.0000

Data Index: 1711761 (The Pile)

Max Activating Token Index: 562

Text #13

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6860. Min Act: -0.0000

Data Index: 1404462 (The Pile)

Max Activating Token Index: 360

Text #14

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1016010 (The Pile)

Max Activating Token Index: 394

Text #15

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6869. Min Act: -0.0000

Data Index: 882726 (The Pile)

Max Activating Token Index: 975

Text #16

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1047191 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6975. Min Act: -0.0000

Data Index: 223991 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7296. Min Act: -0.0000

Data Index: 851999 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6618. Min Act: -0.0000

Data Index: 760986 (The Pile)

Max Activating Token Index: 767