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

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

Neuron 3446 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: 0.3122. Min Range: -0.3122

Max Act: 0.3122. Min Act: -0.0000

Data Index: 573956 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1074746 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2066. Min Act: -0.0000

Data Index: 461640 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1938. Min Act: -0.0000

Data Index: 775114 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2068. Min Act: -0.0000

Data Index: 65267 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2116. Min Act: -0.0000

Data Index: 259003 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1198764 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1826. Min Act: -0.0001

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1787. Min Act: -0.0000

Data Index: 871828 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1969. Min Act: -0.0000

Data Index: 806608 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1615. Min Act: -0.0001

Data Index: 238361 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2007. Min Act: -0.0000

Data Index: 462425 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1837. Min Act: -0.0000

Data Index: 975163 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1922. Min Act: -0.0000

Data Index: 616164 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1795. Min Act: -0.0000

Data Index: 848713 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1815. Min Act: -0.0000

Data Index: 32207 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1676. Min Act: -0.0000

Data Index: 18509 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1883. Min Act: -0.0000

Data Index: 939152 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1292980 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.1543. Min Act: -0.0000

Data Index: 460420 (C4 (Web Text))

Max Activating Token Index: 688