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

Dataset: The Pile

Neuron 1931 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: 1.0667. Min Range: -1.0667

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1994273 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1448969 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.9196. Min Act: -0.0000

Data Index: 35600 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8929. Min Act: -0.0000

Data Index: 328280 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1024490 (The Pile)

Max Activating Token Index: 409

Text #5

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1297641 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7543. Min Act: -0.0000

Data Index: 705653 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1648386 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7247. Min Act: -0.0000

Data Index: 199028 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7387. Min Act: -0.0000

Data Index: 851794 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1080442 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7328. Min Act: -0.0000

Data Index: 743826 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1069610 (The Pile)

Max Activating Token Index: 354

Text #13

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.7156. Min Act: -0.0000

Data Index: 933555 (The Pile)

Max Activating Token Index: 852

Text #14

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1907793 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6959. Min Act: -0.0000

Data Index: 254073 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6929. Min Act: -0.0000

Data Index: 847351 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1414826 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6698. Min Act: -0.0000

Data Index: 961915 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 1.0667. Min Range: -1.0667

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1358364 (The Pile)

Max Activating Token Index: 951