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

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

Neuron 762 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1244523 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0854. Min Act: -0.0002

Data Index: 935429 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0826. Min Act: -0.0002

Data Index: 192016 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1273373 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0002

Data Index: 362787 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0811. Min Act: -0.0002

Data Index: 185569 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0828. Min Act: -0.0002

Data Index: 469863 (C4 (Web Text))

Max Activating Token Index: 720

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0785. Min Act: -0.0002

Data Index: 441219 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1312890 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0796. Min Act: -0.0002

Data Index: 488046 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0801. Min Act: -0.0002

Data Index: 42762 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0796. Min Act: -0.0002

Data Index: 794814 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0763. Min Act: -0.0002

Data Index: 807785 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0767. Min Act: -0.0002

Data Index: 798513 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0788. Min Act: -0.0002

Data Index: 874373 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0800. Min Act: -0.0002

Data Index: 413583 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0742. Min Act: -0.0002

Data Index: 143470 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0774. Min Act: -0.0002

Data Index: 845422 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0821. Min Act: -0.0002

Data Index: 468262 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1161935 (C4 (Web Text))

Max Activating Token Index: 853