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

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

Neuron 680 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: 0.1069. Min Range: -0.1069

Max Act: 0.1069. Min Act: -0.0003

Data Index: 777755 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0986. Min Act: -0.0003

Data Index: 603299 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0859. Min Act: -0.0003

Data Index: 715968 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0910. Min Act: -0.0003

Data Index: 1220346 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.1004. Min Act: -0.0003

Data Index: 1102076 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0994. Min Act: -0.0003

Data Index: 742702 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0993. Min Act: -0.0003

Data Index: 190595 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0923. Min Act: -0.0003

Data Index: 28674 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0985. Min Act: -0.0003

Data Index: 306431 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0919. Min Act: -0.0003

Data Index: 586840 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0951. Min Act: -0.0003

Data Index: 1334051 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0878. Min Act: -0.0003

Data Index: 704856 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0987. Min Act: -0.0003

Data Index: 1126984 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0896. Min Act: -0.0003

Data Index: 1056091 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0811. Min Act: -0.0003

Data Index: 232180 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0890. Min Act: -0.0003

Data Index: 696697 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0878. Min Act: -0.0003

Data Index: 825258 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0812. Min Act: -0.0003

Data Index: 909627 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0841. Min Act: -0.0003

Data Index: 868862 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.1069. Min Range: -0.1069

Max Act: 0.0866. Min Act: -0.0003

Data Index: 313757 (C4 (Web Text))

Max Activating Token Index: 302