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

Dataset: The Pile

Neuron 1933 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1516161 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1936016 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1201514 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3098. Min Act: -0.0000

Data Index: 160966 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1146934 (The Pile)

Max Activating Token Index: 144

Text #5

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2890. Min Act: -0.0000

Data Index: 222514 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2704. Min Act: -0.0000

Data Index: 236764 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2644. Min Act: -0.0000

Data Index: 186097 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2719. Min Act: -0.0000

Data Index: 793202 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2799. Min Act: -0.0000

Data Index: 557407 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2753. Min Act: -0.0000

Data Index: 881054 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1708814 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1585580 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1249490 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2513. Min Act: -0.0000

Data Index: 872157 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2664. Min Act: -0.0000

Data Index: 565949 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2634. Min Act: -0.0000

Data Index: 948369 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2364. Min Act: -0.0000

Data Index: 380763 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2579. Min Act: -0.0000

Data Index: 819847 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2430. Min Act: -0.0000

Data Index: 69524 (The Pile)

Max Activating Token Index: 101