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

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

Neuron 340 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.3242. Min Act: -0.0003

Data Index: 978094 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2773. Min Act: -0.0003

Data Index: 811629 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2683. Min Act: -0.0003

Data Index: 9558 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2486. Min Act: -0.0003

Data Index: 10828 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2304. Min Act: -0.0003

Data Index: 503547 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2276. Min Act: -0.0003

Data Index: 594576 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2189. Min Act: -0.0003

Data Index: 601930 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2213. Min Act: -0.0003

Data Index: 350006 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2112. Min Act: -0.0003

Data Index: 1144916 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2093. Min Act: -0.0003

Data Index: 1328930 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2121. Min Act: -0.0003

Data Index: 170092 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2010. Min Act: -0.0003

Data Index: 998367 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2077. Min Act: -0.0003

Data Index: 957123 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2072. Min Act: -0.0002

Data Index: 1177628 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.2069. Min Act: -0.0003

Data Index: 1312605 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.1983. Min Act: -0.0003

Data Index: 1277329 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.1998. Min Act: -0.0003

Data Index: 1102523 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.1991. Min Act: -0.0003

Data Index: 658992 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.1971. Min Act: -0.0003

Data Index: 644397 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.3242. Min Range: -0.3242

Max Act: 0.1914. Min Act: -0.0003

Data Index: 39665 (C4 (Web Text))

Max Activating Token Index: 681