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

Dataset: The Pile

Neuron 1633 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1219670 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.7371. Min Act: -0.0000

Data Index: 336535 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.6145. Min Act: -0.0000

Data Index: 413164 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.6258. Min Act: -0.0000

Data Index: 618714 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5764. Min Act: -0.0000

Data Index: 589794 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5725. Min Act: -0.0000

Data Index: 253875 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5564. Min Act: -0.0000

Data Index: 242285 (The Pile)

Max Activating Token Index: 254

Text #7

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1795627 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5352. Min Act: -0.0000

Data Index: 159197 (The Pile)

Max Activating Token Index: 111

Text #9

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1716375 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1746746 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1189777 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5519. Min Act: -0.0000

Data Index: 544448 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5206. Min Act: -0.0000

Data Index: 1438345 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4580. Min Act: -0.0000

Data Index: 715132 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5109. Min Act: -0.0000

Data Index: 861522 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4988. Min Act: -0.0000

Data Index: 450453 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.4815. Min Act: -0.0000

Data Index: 469733 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1024516 (The Pile)

Max Activating Token Index: 110

Text #19

Max Range: 0.7371. Min Range: -0.7371

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1083744 (The Pile)

Max Activating Token Index: 279