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

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

Neuron 2470 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0003

Data Index: 229821 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0894. Min Act: -0.0003

Data Index: 1025730 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1074308 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0838. Min Act: -0.0003

Data Index: 38554 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0876. Min Act: -0.0003

Data Index: 1088630 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0840. Min Act: -0.0003

Data Index: 771132 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1169580 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0854. Min Act: -0.0003

Data Index: 239738 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0775. Min Act: -0.0003

Data Index: 289805 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0798. Min Act: -0.0003

Data Index: 316506 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0742. Min Act: -0.0003

Data Index: 598728 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0757. Min Act: -0.0003

Data Index: 617159 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0786. Min Act: -0.0003

Data Index: 351466 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0786. Min Act: -0.0003

Data Index: 1013751 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1239817 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0740. Min Act: -0.0003

Data Index: 874960 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0730. Min Act: -0.0003

Data Index: 804032 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1353529 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0734. Min Act: -0.0003

Data Index: 930580 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1142859 (C4 (Web Text))

Max Activating Token Index: 62