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

Dataset: The Pile

Neuron 4538 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1294824 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0950. Min Act: -0.0000

Data Index: 599109 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1592527 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1326917 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1574727 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0833. Min Act: -0.0000

Data Index: 1001345 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0798. Min Act: -0.0000

Data Index: 98171 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0846. Min Act: -0.0000

Data Index: 207024 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0806. Min Act: -0.0000

Data Index: 421968 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0829. Min Act: -0.0000

Data Index: 849510 (The Pile)

Max Activating Token Index: 840

Text #10

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0829. Min Act: -0.0000

Data Index: 847346 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0775. Min Act: -0.0000

Data Index: 979403 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0784. Min Act: -0.0000

Data Index: 773429 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1085081 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0783. Min Act: -0.0000

Data Index: 492922 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0779. Min Act: -0.0000

Data Index: 380854 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0762. Min Act: -0.0000

Data Index: 791543 (The Pile)

Max Activating Token Index: 75

Text #17

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0704. Min Act: -0.0000

Data Index: 334230 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1181590 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 0.0950. Min Range: -0.0950

Max Act: 0.0774. Min Act: -0.0000

Data Index: 226464 (The Pile)

Max Activating Token Index: 91