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

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

Neuron 606 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1266886 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2400. Min Act: -0.0000

Data Index: 757553 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2215. Min Act: -0.0000

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.2070. Min Act: -0.0000

Data Index: 830970 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1895. Min Act: -0.0000

Data Index: 286949 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1684. Min Act: -0.0000

Data Index: 88215 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1817. Min Act: -0.0000

Data Index: 760868 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1924. Min Act: -0.0000

Data Index: 318734 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1921. Min Act: -0.0000

Data Index: 130111 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1768. Min Act: -0.0000

Data Index: 774224 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1838. Min Act: -0.0000

Data Index: 487326 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1175636 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1824. Min Act: -0.0000

Data Index: 408507 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1741. Min Act: -0.0000

Data Index: 125052 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1746. Min Act: -0.0000

Data Index: 644190 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1730. Min Act: -0.0000

Data Index: 539342 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1711. Min Act: -0.0000

Data Index: 928454 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1703. Min Act: -0.0000

Data Index: 903310 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1651. Min Act: -0.0000

Data Index: 188306 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.2805. Min Range: -0.2805

Max Act: 0.1588. Min Act: -0.0000

Data Index: 838249 (C4 (Web Text))

Max Activating Token Index: 13