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

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

Neuron 489 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: 0.1037. Min Range: -0.1037

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1126819 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1316776 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0925. Min Act: -0.0000

Data Index: 365600 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0907. Min Act: -0.0000

Data Index: 889770 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0935. Min Act: -0.0000

Data Index: 426911 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1153943 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0914. Min Act: -0.0000

Data Index: 524340 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0907. Min Act: -0.0000

Data Index: 112332 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1256627 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0903. Min Act: -0.0000

Data Index: 4206 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0892. Min Act: -0.0000

Data Index: 982350 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1361444 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1177392 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0901. Min Act: -0.0000

Data Index: 868113 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0872. Min Act: -0.0000

Data Index: 841629 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0801. Min Act: -0.0000

Data Index: 189454 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1238356 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1010924 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0817. Min Act: -0.0000

Data Index: 789585 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0824. Min Act: -0.0000

Data Index: 677889 (C4 (Web Text))

Max Activating Token Index: 163