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

Dataset: The Pile

Neuron 4682 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.6504. Min Act: -0.0000

Data Index: 262456 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5176. Min Act: -0.0000

Data Index: 637545 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1021795 (The Pile)

Max Activating Token Index: 867

Text #3

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1722281 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1564004 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1463763 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5007. Min Act: -0.0000

Data Index: 315107 (The Pile)

Max Activating Token Index: 174

Text #7

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1754749 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1006510 (The Pile)

Max Activating Token Index: 803

Text #9

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4918. Min Act: -0.0000

Data Index: 288696 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5064. Min Act: -0.0000

Data Index: 688686 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1878104 (The Pile)

Max Activating Token Index: 626

Text #12

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1748750 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1198755 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1280231 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1815638 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4926. Min Act: -0.0000

Data Index: 687392 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4617. Min Act: -0.0000

Data Index: 281913 (The Pile)

Max Activating Token Index: 822

Text #18

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4834. Min Act: -0.0000

Data Index: 774626 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 0.6504. Min Range: -0.6504

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1535391 (The Pile)

Max Activating Token Index: 287