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

Dataset: The Pile

Neuron 3549 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.8486. Min Act: -0.0000

Data Index: 1502385 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.8049. Min Act: -0.0000

Data Index: 1505994 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.5551. Min Act: -0.0000

Data Index: 1499519 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.5969. Min Act: -0.0000

Data Index: 146009 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.5898. Min Act: -0.0000

Data Index: 782884 (The Pile)

Max Activating Token Index: 632

Text #5

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.4082. Min Act: -0.0000

Data Index: 1814784 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7127. Min Act: -0.0000

Data Index: 998388 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.3324. Min Act: -0.0000

Data Index: 869207 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.3434. Min Act: -0.0000

Data Index: 1482912 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.5991. Min Act: -0.0000

Data Index: 936484 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.2685. Min Act: -0.0000

Data Index: 1982435 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 3.8486. Min Range: -3.8486

Max Act: 2.8570. Min Act: -0.0000

Data Index: 1654097 (The Pile)

Max Activating Token Index: 54

Text #12

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.1421. Min Act: -0.0000

Data Index: 1373423 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.1587. Min Act: -0.0000

Data Index: 221057 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.2939. Min Act: -0.0000

Data Index: 32049 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.4516. Min Act: -0.0000

Data Index: 448251 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.1238. Min Act: -0.0000

Data Index: 1493450 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.2780. Min Act: -0.0000

Data Index: 454495 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 3.8486. Min Range: -3.8486

Max Act: 2.9754. Min Act: -0.0000

Data Index: 1431359 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 3.8486. Min Range: -3.8486

Max Act: 2.9609. Min Act: -0.0000

Data Index: 1837477 (The Pile)

Max Activating Token Index: 672