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

Dataset: The Pile

Neuron 2641 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: 10.6874. Min Range: -10.6874

Max Act: 10.6874. Min Act: -0.0000

Data Index: 464190 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 10.6874. Min Range: -10.6874

Max Act: 10.1715. Min Act: -0.0000

Data Index: 1838047 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.6372. Min Act: -0.0000

Data Index: 182025 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.6870. Min Act: -0.0000

Data Index: 1696285 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.4736. Min Act: -0.0000

Data Index: 1456264 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.7161. Min Act: -0.0000

Data Index: 1357285 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.6999. Min Act: -0.0000

Data Index: 514847 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.8156. Min Act: -0.0000

Data Index: 1930594 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.5012. Min Act: -0.0000

Data Index: 1216412 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.2838. Min Act: -0.0000

Data Index: 1559658 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.2805. Min Act: -0.0000

Data Index: 135161 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.2917. Min Act: -0.0000

Data Index: 1930787 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.4082. Min Act: -0.0000

Data Index: 1223764 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.5472. Min Act: -0.0000

Data Index: 489886 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.3581. Min Act: -0.0000

Data Index: 587313 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.3526. Min Act: -0.0000

Data Index: 626038 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.1598. Min Act: -0.0000

Data Index: 738251 (The Pile)

Max Activating Token Index: 570

Text #17

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.1596. Min Act: -0.0000

Data Index: 1458139 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.3224. Min Act: -0.0000

Data Index: 1709373 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 10.6874. Min Range: -10.6874

Max Act: 9.3170. Min Act: -0.0000

Data Index: 1891051 (The Pile)

Max Activating Token Index: 100