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

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

Neuron 1530 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: 2.4690. Min Range: -2.4690

Max Act: 2.4690. Min Act: -0.0000

Data Index: 332872 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.0327. Min Act: -0.0000

Data Index: 757501 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.1211. Min Act: -0.0000

Data Index: 468148 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.1928. Min Act: -0.0000

Data Index: 828149 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.2327. Min Act: -0.0000

Data Index: 163568 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.2725. Min Act: -0.0000

Data Index: 26713 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.1131. Min Act: -0.0000

Data Index: 1220145 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.1076. Min Act: -0.0000

Data Index: 833926 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.9571. Min Act: -0.0000

Data Index: 191007 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.2397. Min Act: -0.0000

Data Index: 772010 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.0059. Min Act: -0.0000

Data Index: 704441 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.9943. Min Act: -0.0000

Data Index: 1041924 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.0003. Min Act: 0.0001

Data Index: 805096 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 2.4690. Min Range: -2.4690

Max Act: 2.0623. Min Act: -0.0000

Data Index: 1277128 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.9186. Min Act: -0.0000

Data Index: 649172 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.8201. Min Act: -0.0000

Data Index: 497858 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.9029. Min Act: -0.0000

Data Index: 955948 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1356477 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.8886. Min Act: -0.0000

Data Index: 1341391 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 2.4690. Min Range: -2.4690

Max Act: 1.8715. Min Act: -0.0000

Data Index: 488240 (C4 (Web Text))

Max Activating Token Index: 359