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

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

Neuron 3346 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0000

Data Index: 743100 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2180. Min Act: -0.0000

Data Index: 780934 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2079. Min Act: -0.0000

Data Index: 202483 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1153987 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1976. Min Act: -0.0000

Data Index: 750693 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1915. Min Act: -0.0000

Data Index: 336560 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1246757 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1296596 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1081779 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1852. Min Act: -0.0000

Data Index: 1332175 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1656073 (Python Code)

Max Activating Token Index: 769

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1873. Min Act: -0.0000

Data Index: 898434 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1866. Min Act: -0.0000

Data Index: 351543 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1799. Min Act: -0.0000

Data Index: 793658 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1706. Min Act: -0.0000

Data Index: 506592 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1764. Min Act: -0.0000

Data Index: 618029 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1276050 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1185575 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1754. Min Act: -0.0000

Data Index: 501873 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1743. Min Act: -0.0000

Data Index: 646182 (C4 (Web Text))

Max Activating Token Index: 565