Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.9909. Min Act: -0.0000

Data Index: 764143 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1796381 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5482. Min Act: -0.0000

Data Index: 557176 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1340289 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1756393 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5377. Min Act: -0.0000

Data Index: 876937 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5260. Min Act: -0.0000

Data Index: 414385 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1824397 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5163. Min Act: -0.0000

Data Index: 774838 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5015. Min Act: -0.0000

Data Index: 511073 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1695410 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1113984 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.5169. Min Act: -0.0000

Data Index: 504456 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4864. Min Act: -0.0000

Data Index: 758366 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1384787 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4791. Min Act: -0.0000

Data Index: 970531 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1279264 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4733. Min Act: 0.0000

Data Index: 271182 (The Pile)

Max Activating Token Index: 302

Text #18

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4975. Min Act: -0.0000

Data Index: 518349 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.9909. Min Range: -0.9909

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1972662 (The Pile)

Max Activating Token Index: 731