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

Dataset: The Pile

Neuron 1587 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: 0.7881. Min Range: -0.7881

Max Act: 0.7881. Min Act: -0.0000

Data Index: 58431 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6724. Min Act: -0.0000

Data Index: 409932 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1527667 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.7341. Min Act: -0.0000

Data Index: 106943 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5876. Min Act: -0.0000

Data Index: 48019 (The Pile)

Max Activating Token Index: 627

Text #5

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1048676 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1200230 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5986. Min Act: -0.0000

Data Index: 817379 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1981494 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5777. Min Act: -0.0000

Data Index: 754754 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1213445 (The Pile)

Max Activating Token Index: 559

Text #11

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5404. Min Act: -0.0000

Data Index: 483887 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5878. Min Act: -0.0000

Data Index: 302699 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5589. Min Act: -0.0000

Data Index: 271792 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5250. Min Act: -0.0000

Data Index: 102639 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1849572 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5494. Min Act: -0.0000

Data Index: 398097 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1696563 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5334. Min Act: -0.0000

Data Index: 177936 (The Pile)

Max Activating Token Index: 710

Text #19

Max Range: 0.7881. Min Range: -0.7881

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1679422 (The Pile)

Max Activating Token Index: 587