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

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

Neuron 4306 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1323453 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2079. Min Act: -0.0000

Data Index: 593266 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2044. Min Act: -0.0000

Data Index: 674208 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1933. Min Act: -0.0000

Data Index: 573689 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1063046 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1786. Min Act: -0.0000

Data Index: 959633 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1762. Min Act: -0.0000

Data Index: 494959 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1721. Min Act: -0.0000

Data Index: 175864 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1741. Min Act: -0.0000

Data Index: 290148 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1665. Min Act: -0.0000

Data Index: 113021 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1707. Min Act: -0.0000

Data Index: 228018 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1720. Min Act: -0.0000

Data Index: 506052 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1136032 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1145279 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1609. Min Act: -0.0000

Data Index: 597850 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1249631 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1486. Min Act: -0.0000

Data Index: 777174 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1549. Min Act: -0.0000

Data Index: 43258 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1601. Min Act: -0.0000

Data Index: 992208 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1106390 (C4 (Web Text))

Max Activating Token Index: 22