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

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

Neuron 4278 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0001

Data Index: 924936 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1048704 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0801. Min Act: -0.0001

Data Index: 131202 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0797. Min Act: -0.0001

Data Index: 606076 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0869. Min Act: -0.0001

Data Index: 947550 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0787. Min Act: -0.0001

Data Index: 479846 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1294274 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0812. Min Act: -0.0001

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0836. Min Act: -0.0001

Data Index: 776809 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0715. Min Act: -0.0001

Data Index: 8595 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0737. Min Act: -0.0001

Data Index: 807893 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0777. Min Act: -0.0001

Data Index: 47792 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1005963 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0662. Min Act: -0.0001

Data Index: 605155 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0661. Min Act: -0.0001

Data Index: 455231 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0656. Min Act: -0.0001

Data Index: 300621 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0701. Min Act: -0.0001

Data Index: 70933 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0690. Min Act: -0.0001

Data Index: 82370 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0720. Min Act: -0.0001

Data Index: 321760 (C4 (Web Text))

Max Activating Token Index: 600