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

Dataset: The Pile

Neuron 3813 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: 1.7914. Min Range: -1.7914

Max Act: 1.7914. Min Act: -0.0000

Data Index: 357676 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7246. Min Act: -0.0000

Data Index: 1837445 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7106. Min Act: -0.0000

Data Index: 311530 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5906. Min Act: -0.0000

Data Index: 697647 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5549. Min Act: -0.0000

Data Index: 1566906 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4867. Min Act: -0.0000

Data Index: 999286 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5677. Min Act: -0.0000

Data Index: 265301 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5906. Min Act: -0.0000

Data Index: 1035914 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4629. Min Act: 0.0000

Data Index: 1222513 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5399. Min Act: -0.0000

Data Index: 754579 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5341. Min Act: -0.0000

Data Index: 695034 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5223. Min Act: -0.0000

Data Index: 1249898 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5936. Min Act: -0.0000

Data Index: 752404 (The Pile)

Max Activating Token Index: 342

Text #13

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5639. Min Act: -0.0000

Data Index: 518634 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4037. Min Act: 0.0000

Data Index: 1044356 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5361. Min Act: -0.0000

Data Index: 438396 (The Pile)

Max Activating Token Index: 955

Text #16

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4309. Min Act: -0.0000

Data Index: 62742 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4144. Min Act: -0.0000

Data Index: 771317 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.5324. Min Act: -0.0000

Data Index: 650363 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1453403 (The Pile)

Max Activating Token Index: 699