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

Dataset: The Pile

Neuron 3792 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: 0.4582. Min Range: -0.4582

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1244359 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4582. Min Act: -0.0000

Data Index: 870332 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4097. Min Act: -0.0000

Data Index: 419745 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4267. Min Act: -0.0000

Data Index: 429195 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3984. Min Act: -0.0000

Data Index: 363210 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4102. Min Act: -0.0000

Data Index: 417663 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1592255 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3439. Min Act: -0.0000

Data Index: 509181 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3628. Min Act: -0.0000

Data Index: 511332 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3922. Min Act: -0.0000

Data Index: 255274 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3641. Min Act: -0.0000

Data Index: 309796 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1146626 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1022715 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1479650 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1254398 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3828. Min Act: -0.0000

Data Index: 5825 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1739588 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3495. Min Act: -0.0000

Data Index: 992074 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1078286 (The Pile)

Max Activating Token Index: 668

Text #19

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3222. Min Act: -0.0000

Data Index: 437389 (The Pile)

Max Activating Token Index: 691