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

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

Neuron 5801 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: 0.1409. Min Range: -0.1409

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1326502 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1097. Min Act: -0.0002

Data Index: 976951 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0982. Min Act: -0.0002

Data Index: 590371 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0931. Min Act: -0.0002

Data Index: 29762 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0901. Min Act: -0.0002

Data Index: 692625 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0909. Min Act: -0.0002

Data Index: 273347 (C4 (Web Text))

Max Activating Token Index: 864

Text #6

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0899. Min Act: -0.0002

Data Index: 865087 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0895. Min Act: -0.0002

Data Index: 892631 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0857. Min Act: -0.0002

Data Index: 466466 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1140189 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0866. Min Act: -0.0002

Data Index: 193167 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0886. Min Act: -0.0002

Data Index: 919616 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0839. Min Act: -0.0002

Data Index: 445373 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0828. Min Act: -0.0002

Data Index: 439865 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0824. Min Act: -0.0002

Data Index: 215859 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0820. Min Act: -0.0002

Data Index: 64680 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1164578 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0792. Min Act: -0.0002

Data Index: 363935 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0784. Min Act: -0.0002

Data Index: 620590 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0770. Min Act: -0.0002

Data Index: 146606 (C4 (Web Text))

Max Activating Token Index: 215