Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1012 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.2336. Min Act: -0.0001

Data Index: 984958 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1980. Min Act: -0.0001

Data Index: 213805 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1264178 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1896. Min Act: -0.0001

Data Index: 303779 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1790. Min Act: -0.0001

Data Index: 890140 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1847. Min Act: -0.0001

Data Index: 1267252 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1778. Min Act: -0.0001

Data Index: 920188 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1777. Min Act: -0.0001

Data Index: 396192 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1356436 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1574322 (Python Code)

Max Activating Token Index: 571

Text #10

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1788. Min Act: -0.0000

Data Index: 1024353 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1841. Min Act: -0.0001

Data Index: 106064 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1781. Min Act: -0.0001

Data Index: 878804 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1840. Min Act: -0.0001

Data Index: 627986 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1820. Min Act: -0.0001

Data Index: 851220 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1715. Min Act: -0.0001

Data Index: 551820 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1759. Min Act: -0.0001

Data Index: 174416 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1033601 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1457809 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 0.2336. Min Range: -0.2336

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1604727 (Python Code)

Max Activating Token Index: 554