Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0852. Min Act: -0.0002

Data Index: 245378 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0839. Min Act: -0.0002

Data Index: 37921 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0878. Min Act: -0.0002

Data Index: 56505 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1095741 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0827. Min Act: -0.0002

Data Index: 701746 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1310923 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0792. Min Act: -0.0002

Data Index: 535687 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0787. Min Act: -0.0003

Data Index: 188002 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1262751 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0765. Min Act: -0.0002

Data Index: 124432 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0798. Min Act: -0.0003

Data Index: 35049 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0764. Min Act: -0.0002

Data Index: 324503 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0743. Min Act: -0.0003

Data Index: 117364 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0741. Min Act: -0.0003

Data Index: 398763 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0752. Min Act: -0.0003

Data Index: 369547 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1035975 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0756. Min Act: -0.0003

Data Index: 722243 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1171104 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0737. Min Act: -0.0002

Data Index: 69196 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.0878. Min Range: -0.0878

Max Act: 0.0711. Min Act: -0.0003

Data Index: 483319 (C4 (Web Text))

Max Activating Token Index: 445