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

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

Neuron 2024 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.3525. Min Act: -0.0000

Data Index: 947767 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.3406. Min Act: -0.0000

Data Index: 659626 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.2751. Min Act: -0.0000

Data Index: 518822 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.3849. Min Act: -0.0000

Data Index: 826073 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.1153. Min Act: -0.0000

Data Index: 218892 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.3209. Min Act: -0.0000

Data Index: 955343 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.1867. Min Act: -0.0000

Data Index: 82825 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.1715. Min Act: -0.0000

Data Index: 586769 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.1389. Min Act: -0.0000

Data Index: 156526 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0851. Min Act: -0.0000

Data Index: 1098218 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0861. Min Act: -0.0000

Data Index: 624219 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0513. Min Act: -0.0000

Data Index: 674091 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0587. Min Act: -0.0000

Data Index: 968972 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.9318. Min Act: -0.0000

Data Index: 662404 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.9200. Min Act: -0.0000

Data Index: 799097 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.8718. Min Act: -0.0000

Data Index: 822712 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0857. Min Act: -0.0000

Data Index: 1327953 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.9640. Min Act: -0.0000

Data Index: 727723 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.9377. Min Act: -0.0000

Data Index: 76169 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0370. Min Act: -0.0000

Data Index: 697036 (C4 (Web Text))

Max Activating Token Index: 815