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

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

Neuron 4863 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1258754 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0922. Min Act: -0.0002

Data Index: 556384 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0853. Min Act: -0.0002

Data Index: 890581 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0874. Min Act: -0.0002

Data Index: 531281 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0875. Min Act: -0.0002

Data Index: 800623 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0836. Min Act: -0.0002

Data Index: 993160 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0872. Min Act: -0.0002

Data Index: 90493 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0857. Min Act: -0.0002

Data Index: 964751 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0779. Min Act: -0.0002

Data Index: 557330 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0782. Min Act: -0.0002

Data Index: 415556 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0845. Min Act: -0.0002

Data Index: 5290 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0807. Min Act: -0.0002

Data Index: 299233 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1356789 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0794. Min Act: -0.0002

Data Index: 932998 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0748. Min Act: -0.0002

Data Index: 178802 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0820. Min Act: -0.0002

Data Index: 113318 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1209045 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0749. Min Act: -0.0002

Data Index: 196385 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0805. Min Act: -0.0002

Data Index: 618260 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0739. Min Act: -0.0002

Data Index: 538158 (C4 (Web Text))

Max Activating Token Index: 973