Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 314 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.2112. Min Act: -0.0001

Data Index: 696367 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.2091. Min Act: -0.0001

Data Index: 1213029 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.2005. Min Act: -0.0001

Data Index: 750020 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1988. Min Act: -0.0001

Data Index: 250629 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1770. Min Act: -0.0001

Data Index: 238381 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1924. Min Act: -0.0001

Data Index: 333793 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1783. Min Act: -0.0001

Data Index: 801947 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1116956 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1812. Min Act: -0.0001

Data Index: 312785 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1859. Min Act: -0.0001

Data Index: 106871 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1798. Min Act: -0.0001

Data Index: 424955 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1714. Min Act: -0.0001

Data Index: 6791 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1049264 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1636. Min Act: -0.0001

Data Index: 50784 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1690. Min Act: -0.0001

Data Index: 721443 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1965 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1741. Min Act: -0.0001

Data Index: 187797 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1631. Min Act: -0.0001

Data Index: 883826 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1874. Min Act: -0.0001

Data Index: 343860 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.2112. Min Range: -0.2112

Max Act: 0.1653. Min Act: -0.0001

Data Index: 576926 (C4 (Web Text))

Max Activating Token Index: 103