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

Dataset: The Pile

Neuron 3510 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.5251. Min Act: -0.0000

Data Index: 3902 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4242. Min Act: -0.0000

Data Index: 943188 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4319. Min Act: -0.0000

Data Index: 495000 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4017. Min Act: -0.0000

Data Index: 1069823 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3692. Min Act: -0.0000

Data Index: 980390 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4014. Min Act: -0.0000

Data Index: 80433 (The Pile)

Max Activating Token Index: 637

Text #6

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3742. Min Act: -0.0000

Data Index: 653834 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3911. Min Act: -0.0000

Data Index: 785603 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3813. Min Act: -0.0000

Data Index: 522624 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1657556 (The Pile)

Max Activating Token Index: 998

Text #10

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3497. Min Act: -0.0000

Data Index: 500693 (The Pile)

Max Activating Token Index: 983

Text #11

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1899564 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1897971 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3636. Min Act: -0.0000

Data Index: 817350 (The Pile)

Max Activating Token Index: 599

Text #14

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1213064 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3819. Min Act: -0.0000

Data Index: 308309 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3626. Min Act: -0.0000

Data Index: 83898 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3635. Min Act: -0.0000

Data Index: 928955 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3442. Min Act: -0.0000

Data Index: 291064 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3330. Min Act: -0.0000

Data Index: 62322 (The Pile)

Max Activating Token Index: 273