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

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

Neuron 3457 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2832. Min Act: -0.0000

Data Index: 316686 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2707. Min Act: -0.0000

Data Index: 1275211 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1643065 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1069354 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2274. Min Act: -0.0000

Data Index: 888122 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2172. Min Act: -0.0000

Data Index: 44135 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2124. Min Act: -0.0000

Data Index: 72222 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1393224 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1350030 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1167662 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1602691 (Python Code)

Max Activating Token Index: 961

Text #11

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2031. Min Act: -0.0000

Data Index: 58052 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1973. Min Act: -0.0000

Data Index: 918010 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1950. Min Act: -0.0000

Data Index: 134226 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1409450 (Python Code)

Max Activating Token Index: 844

Text #15

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1973. Min Act: -0.0000

Data Index: 671680 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1827. Min Act: 0.0001

Data Index: 1567897 (Python Code)

Max Activating Token Index: 980

Text #17

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1986. Min Act: -0.0000

Data Index: 724307 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.1809. Min Act: -0.0000

Data Index: 792081 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.2832. Min Range: -0.2832

Max Act: 0.2023. Min Act: -0.0000

Data Index: 1402706 (Python Code)

Max Activating Token Index: 816