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

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

Neuron 1884 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: 0.0945. Min Range: -0.0945

Max Act: 0.0945. Min Act: -0.0002

Data Index: 795246 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0921. Min Act: -0.0001

Data Index: 880399 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1219964 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0876. Min Act: -0.0001

Data Index: 424481 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0842. Min Act: -0.0002

Data Index: 154627 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0865. Min Act: -0.0001

Data Index: 100217 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0812. Min Act: -0.0001

Data Index: 319026 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1315095 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0798. Min Act: 0.0000

Data Index: 98085 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0794. Min Act: 0.0000

Data Index: 589782 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0803. Min Act: 0.0000

Data Index: 542925 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0757. Min Act: -0.0002

Data Index: 410394 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0767. Min Act: 0.0000

Data Index: 765916 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0792. Min Act: -0.0001

Data Index: 346705 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0782. Min Act: -0.0002

Data Index: 125927 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1160953 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1042842 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1311797 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0746. Min Act: -0.0002

Data Index: 907191 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0754. Min Act: -0.0001

Data Index: 515787 (C4 (Web Text))

Max Activating Token Index: 65