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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3737 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4761. Min Act: -0.0000

Data Index: 339281 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4910. Min Act: -0.0000

Data Index: 738313 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4617. Min Act: -0.0000

Data Index: 733577 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4496. Min Act: -0.0000

Data Index: 351754 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4620. Min Act: -0.0000

Data Index: 282258 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1038813 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3911. Min Act: -0.0000

Data Index: 356776 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4030. Min Act: -0.0000

Data Index: 772920 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1339858 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4447. Min Act: -0.0000

Data Index: 27889 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1045287 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3584. Min Act: -0.0000

Data Index: 488469 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3922. Min Act: -0.0000

Data Index: 524108 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3534. Min Act: -0.0000

Data Index: 679041 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3240. Min Act: -0.0000

Data Index: 883599 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3328. Min Act: -0.0000

Data Index: 734438 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1035003 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3086. Min Act: -0.0000

Data Index: 324319 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.3160. Min Act: -0.0000

Data Index: 606321 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.4910. Min Range: -0.4910

Max Act: 0.2974. Min Act: -0.0000

Data Index: 689217 (C4 (Web Text))

Max Activating Token Index: 832