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

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

Neuron 2506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2499. Min Act: -0.0000

Data Index: 407775 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2299. Min Act: -0.0000

Data Index: 364654 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2211. Min Act: -0.0000

Data Index: 644058 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2108. Min Act: -0.0001

Data Index: 551423 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2101. Min Act: -0.0001

Data Index: 837899 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2204. Min Act: -0.0000

Data Index: 380790 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2170. Min Act: -0.0000

Data Index: 351376 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1003047 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2066. Min Act: -0.0001

Data Index: 781521 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1285329 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.2006. Min Act: -0.0001

Data Index: 372929 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1343584 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1912. Min Act: -0.0001

Data Index: 929680 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1886. Min Act: -0.0001

Data Index: 621599 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1216752 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1811. Min Act: -0.0000

Data Index: 995081 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1868. Min Act: -0.0000

Data Index: 582226 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1828. Min Act: -0.0000

Data Index: 681779 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1753. Min Act: -0.0000

Data Index: 38840 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.2499. Min Range: -0.2499

Max Act: 0.1743. Min Act: -0.0001

Data Index: 741254 (C4 (Web Text))

Max Activating Token Index: 868