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

Dataset: The Pile

Neuron 2672 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1814594 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.7759. Min Act: -0.0000

Data Index: 308938 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.7126. Min Act: -0.0000

Data Index: 1654646 (The Pile)

Max Activating Token Index: 867

Text #3

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1805283 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6373. Min Act: -0.0000

Data Index: 491924 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5993. Min Act: -0.0000

Data Index: 281528 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1048984 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6062. Min Act: -0.0000

Data Index: 10220 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6084. Min Act: -0.0000

Data Index: 94470 (The Pile)

Max Activating Token Index: 855

Text #9

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5546. Min Act: -0.0000

Data Index: 779765 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1997529 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1877406 (The Pile)

Max Activating Token Index: 908

Text #12

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5820. Min Act: -0.0000

Data Index: 538320 (The Pile)

Max Activating Token Index: 192

Text #13

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1451550 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1172565 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1854768 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4946. Min Act: -0.0000

Data Index: 975699 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5641. Min Act: -0.0000

Data Index: 290605 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5303. Min Act: -0.0000

Data Index: 465386 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1020857 (The Pile)

Max Activating Token Index: 800