Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3612 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2383. Min Act: -0.0001

Data Index: 338186 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2031. Min Act: -0.0001

Data Index: 904534 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1309843 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2077. Min Act: -0.0001

Data Index: 914398 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.2144. Min Act: -0.0000

Data Index: 115614 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1178994 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1349405 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1990. Min Act: -0.0001

Data Index: 72280 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1986. Min Act: -0.0001

Data Index: 700079 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1957. Min Act: -0.0001

Data Index: 87432 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1893. Min Act: -0.0000

Data Index: 647911 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1832. Min Act: -0.0001

Data Index: 373579 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1875. Min Act: -0.0000

Data Index: 860821 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1804. Min Act: 0.0000

Data Index: 1129876 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1194639 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1799. Min Act: -0.0001

Data Index: 297448 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1585816 (Python Code)

Max Activating Token Index: 315

Text #17

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1061011 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1712. Min Act: -0.0001

Data Index: 1099299 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.2383. Min Range: -0.2383

Max Act: 0.1805. Min Act: -0.0001

Data Index: 296226 (C4 (Web Text))

Max Activating Token Index: 560