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

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

Neuron 1993 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8071. Min Range: -4.8071

Max Act: 4.6025. Min Act: -0.0001

Data Index: 157376 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 4.8071. Min Range: -4.8071

Max Act: 4.8071. Min Act: -0.0001

Data Index: 132516 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 4.8071. Min Range: -4.8071

Max Act: 4.7674. Min Act: -0.0001

Data Index: 506155 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 4.8071. Min Range: -4.8071

Max Act: 4.0346. Min Act: -0.0001

Data Index: 90691 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.9893. Min Act: -0.0001

Data Index: 1275727 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 4.8071. Min Range: -4.8071

Max Act: 4.0072. Min Act: -0.0001

Data Index: 447651 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.9262. Min Act: -0.0001

Data Index: 1066912 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.7541. Min Act: -0.0001

Data Index: 1268257 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.7360. Min Act: -0.0000

Data Index: 1029916 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.9083. Min Act: -0.0000

Data Index: 1061151 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.6063. Min Act: -0.0001

Data Index: 1350740 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.7265. Min Act: -0.0001

Data Index: 299964 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.8771. Min Act: -0.0000

Data Index: 715134 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 4.8071. Min Range: -4.8071

Max Act: 4.1664. Min Act: -0.0001

Data Index: 583356 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.8211. Min Act: -0.0000

Data Index: 1082903 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.4933. Min Act: -0.0001

Data Index: 558314 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.7959. Min Act: -0.0001

Data Index: 6299 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.4804. Min Act: -0.0001

Data Index: 1210024 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.8097. Min Act: -0.0001

Data Index: 829537 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 4.8071. Min Range: -4.8071

Max Act: 3.7755. Min Act: -0.0001

Data Index: 902493 (C4 (Web Text))

Max Activating Token Index: 477