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

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

Neuron 3376 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1155. Min Act: -0.0002

Data Index: 180410 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1115870 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1033. Min Act: -0.0002

Data Index: 534313 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.1090. Min Act: -0.0002

Data Index: 170450 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0978. Min Act: -0.0002

Data Index: 506134 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0933. Min Act: -0.0002

Data Index: 816619 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0919. Min Act: -0.0002

Data Index: 66482 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0913. Min Act: -0.0002

Data Index: 897902 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1161011 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0915. Min Act: -0.0002

Data Index: 576587 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0873. Min Act: -0.0002

Data Index: 427310 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0896. Min Act: -0.0002

Data Index: 903924 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0929. Min Act: -0.0002

Data Index: 319013 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1054179 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0889. Min Act: -0.0002

Data Index: 849432 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0883. Min Act: -0.0002

Data Index: 47426 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0874. Min Act: -0.0002

Data Index: 810724 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0871. Min Act: -0.0002

Data Index: 165866 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0897. Min Act: -0.0002

Data Index: 997324 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.1155. Min Range: -0.1155

Max Act: 0.0861. Min Act: -0.0002

Data Index: 503095 (C4 (Web Text))

Max Activating Token Index: 603