Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1459 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0006

Data Index: 967235 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0855. Min Act: -0.0006

Data Index: 5859 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0833. Min Act: -0.0006

Data Index: 1148541 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0830. Min Act: -0.0006

Data Index: 770109 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0833. Min Act: -0.0006

Data Index: 408491 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0811. Min Act: -0.0006

Data Index: 974012 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0808. Min Act: -0.0006

Data Index: 46810 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0788. Min Act: -0.0006

Data Index: 216939 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0799. Min Act: -0.0006

Data Index: 1083971 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0800. Min Act: -0.0006

Data Index: 526822 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0763. Min Act: -0.0006

Data Index: 228552 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0772. Min Act: -0.0006

Data Index: 716765 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0787. Min Act: -0.0006

Data Index: 1108150 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0805. Min Act: -0.0006

Data Index: 649921 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0777. Min Act: -0.0006

Data Index: 666634 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0786. Min Act: -0.0006

Data Index: 1042038 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0753. Min Act: -0.0006

Data Index: 700349 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0752. Min Act: -0.0006

Data Index: 28116 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0745. Min Act: -0.0006

Data Index: 120799 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0744. Min Act: -0.0006

Data Index: 836513 (C4 (Web Text))

Max Activating Token Index: 142