Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1334 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2008. Min Range: -3.2008

Max Act: 3.2008. Min Act: -0.0000

Data Index: 459669 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.2008. Min Range: -3.2008

Max Act: 3.0846. Min Act: -0.0000

Data Index: 617567 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 3.2008. Min Range: -3.2008

Max Act: 3.0376. Min Act: -0.0000

Data Index: 848102 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.7852. Min Act: -0.0000

Data Index: 672745 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 3.2008. Min Range: -3.2008

Max Act: 3.0696. Min Act: -0.0000

Data Index: 571160 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.6052. Min Act: -0.0000

Data Index: 263432 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.7370. Min Act: -0.0000

Data Index: 303672 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.7109. Min Act: -0.0000

Data Index: 1223045 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.5674. Min Act: -0.0000

Data Index: 520677 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.4876. Min Act: -0.0000

Data Index: 827882 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.4754. Min Act: -0.0000

Data Index: 554489 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.6783. Min Act: -0.0000

Data Index: 845212 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.5268. Min Act: -0.0000

Data Index: 799550 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.5351. Min Act: -0.0000

Data Index: 135012 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.5090. Min Act: -0.0000

Data Index: 985552 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.5056. Min Act: -0.0000

Data Index: 845981 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.7267. Min Act: -0.0000

Data Index: 920525 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.3017. Min Act: -0.0000

Data Index: 484750 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.4090. Min Act: -0.0000

Data Index: 588586 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 3.2008. Min Range: -3.2008

Max Act: 2.1232. Min Act: -0.0000

Data Index: 180967 (C4 (Web Text))

Max Activating Token Index: 870