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

Dataset: The Pile

Neuron 4157 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: 0.3619. Min Range: -0.3619

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1395384 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3506. Min Act: -0.0000

Data Index: 762395 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3208. Min Act: -0.0000

Data Index: 26110 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1961818 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2926. Min Act: -0.0000

Data Index: 449948 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2939. Min Act: -0.0000

Data Index: 919997 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3041. Min Act: -0.0000

Data Index: 9415 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2839. Min Act: -0.0000

Data Index: 574477 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3019. Min Act: -0.0000

Data Index: 700223 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2797. Min Act: -0.0000

Data Index: 946116 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1197962 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1389623 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1066027 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2829. Min Act: -0.0000

Data Index: 578799 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2820. Min Act: -0.0000

Data Index: 869427 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2718. Min Act: -0.0000

Data Index: 658254 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1045047 (The Pile)

Max Activating Token Index: 433

Text #17

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1778999 (The Pile)

Max Activating Token Index: 49

Text #18

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1492780 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1861615 (The Pile)

Max Activating Token Index: 928