Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1569 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.8360. Min Act: -0.0000

Data Index: 297688 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7904. Min Act: -0.0000

Data Index: 397466 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7889. Min Act: -0.0000

Data Index: 217704 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.7230. Min Act: -0.0000

Data Index: 612937 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6758. Min Act: -0.0000

Data Index: 661069 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6329. Min Act: -0.0000

Data Index: 272922 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6945. Min Act: -0.0000

Data Index: 401156 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6531. Min Act: -0.0000

Data Index: 76738 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6061. Min Act: -0.0000

Data Index: 788827 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5733. Min Act: -0.0000

Data Index: 114246 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6599. Min Act: -0.0000

Data Index: 115869 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1091463 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5902. Min Act: -0.0000

Data Index: 654425 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1215854 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6117. Min Act: -0.0000

Data Index: 793481 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5890. Min Act: -0.0000

Data Index: 689166 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.6237. Min Act: -0.0000

Data Index: 102848 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5612. Min Act: -0.0000

Data Index: 814706 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1036721 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.8360. Min Range: -0.8360

Max Act: 0.5363. Min Act: -0.0000

Data Index: 59617 (C4 (Web Text))

Max Activating Token Index: 296