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

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

Neuron 1669 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: 0.0832. Min Range: -0.0832

Max Act: 0.0777. Min Act: -0.0003

Data Index: 293771 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0774. Min Act: -0.0003

Data Index: 1151993 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0003

Data Index: 153482 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0749. Min Act: -0.0003

Data Index: 350233 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0774. Min Act: -0.0003

Data Index: 1209465 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0766. Min Act: -0.0003

Data Index: 1261061 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1045380 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0746. Min Act: -0.0003

Data Index: 1351304 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0768. Min Act: -0.0003

Data Index: 544864 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0563. Min Act: -0.0003

Data Index: 322569 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0765. Min Act: -0.0003

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1251604 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0686. Min Act: -0.0003

Data Index: 544919 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1249555 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0781. Min Act: -0.0003

Data Index: 138927 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1166901 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1089167 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0665. Min Act: -0.0003

Data Index: 118945 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1181009 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0710. Min Act: -0.0003

Data Index: 826055 (C4 (Web Text))

Max Activating Token Index: 821