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

Dataset: The Pile

Neuron 3101 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.6792. Min Act: 0.0000

Data Index: 1990210 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.6454. Min Act: -0.0000

Data Index: 795855 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5527. Min Act: 0.0001

Data Index: 626963 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.5273. Min Act: -0.0000

Data Index: 276325 (The Pile)

Max Activating Token Index: 153

Text #4

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4564. Min Act: -0.0000

Data Index: 952978 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4341. Min Act: -0.0000

Data Index: 558792 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4551. Min Act: -0.0000

Data Index: 1629494 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4252. Min Act: 0.0000

Data Index: 1122877 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1146790 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1186576 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4110. Min Act: -0.0000

Data Index: 691660 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.3929. Min Act: -0.0000

Data Index: 729905 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1422366 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1505264 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4232. Min Act: -0.0000

Data Index: 789076 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1278108 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.3938. Min Act: -0.0000

Data Index: 46317 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1791417 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1771042 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 0.6792. Min Range: -0.6792

Max Act: 0.3958. Min Act: -0.0000

Data Index: 929002 (The Pile)

Max Activating Token Index: 182