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

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

Neuron 2889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3291. Min Act: -0.0001

Data Index: 128740 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1238629 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2266. Min Act: -0.0001

Data Index: 744152 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1082162 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2125. Min Act: -0.0001

Data Index: 505918 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2007. Min Act: -0.0001

Data Index: 1281644 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1995. Min Act: -0.0001

Data Index: 1123353 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1948. Min Act: -0.0001

Data Index: 262139 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2059. Min Act: -0.0001

Data Index: 197595 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2008. Min Act: -0.0001

Data Index: 872831 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2007. Min Act: -0.0001

Data Index: 1124552 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1239182 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1820. Min Act: -0.0001

Data Index: 452159 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1742. Min Act: -0.0001

Data Index: 600978 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1930. Min Act: -0.0001

Data Index: 200183 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1797. Min Act: -0.0001

Data Index: 550810 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1150122 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1732. Min Act: -0.0001

Data Index: 25362 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1719. Min Act: -0.0001

Data Index: 602231 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.1839. Min Act: -0.0001

Data Index: 621201 (C4 (Web Text))

Max Activating Token Index: 33