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

Dataset: The Pile

Neuron 2450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 844354 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8675. Min Act: -0.0000

Data Index: 51467 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1932210 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1392499 (The Pile)

Max Activating Token Index: 167

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1469516 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1945477 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7635. Min Act: -0.0000

Data Index: 890023 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1270875 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8005. Min Act: -0.0000

Data Index: 960845 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7787. Min Act: -0.0000

Data Index: 569540 (The Pile)

Max Activating Token Index: 431

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7667. Min Act: -0.0000

Data Index: 852031 (The Pile)

Max Activating Token Index: 272

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7108. Min Act: -0.0000

Data Index: 684212 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1807895 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7220. Min Act: -0.0000

Data Index: 951209 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7505. Min Act: -0.0000

Data Index: 357754 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1373709 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7104. Min Act: -0.0000

Data Index: 71959 (The Pile)

Max Activating Token Index: 784

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6630. Min Act: -0.0000

Data Index: 8837 (The Pile)

Max Activating Token Index: 732

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6608. Min Act: -0.0000

Data Index: 859423 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1689773 (The Pile)

Max Activating Token Index: 617