Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1421. Min Act: -0.0000

Data Index: 272903 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1077. Min Act: -0.0000

Data Index: 799295 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1044. Min Act: -0.0000

Data Index: 626481 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1265714 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1014. Min Act: -0.0000

Data Index: 574797 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1000. Min Act: -0.0000

Data Index: 673432 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0991. Min Act: -0.0000

Data Index: 647819 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1333661 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0930. Min Act: -0.0000

Data Index: 857246 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1315911 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0945. Min Act: -0.0000

Data Index: 344060 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0898. Min Act: -0.0000

Data Index: 561902 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0937. Min Act: -0.0000

Data Index: 478016 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0934. Min Act: -0.0000

Data Index: 567995 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1247150 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0916. Min Act: -0.0000

Data Index: 121466 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1649620 (Python Code)

Max Activating Token Index: 162

Text #17

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0878. Min Act: -0.0000

Data Index: 960670 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1649775 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0910. Min Act: -0.0000

Data Index: 840747 (C4 (Web Text))

Max Activating Token Index: 57