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

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

Neuron 3611 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.5149. Min Act: -0.0000

Data Index: 842601 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.2736. Min Act: 0.0000

Data Index: 563508 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.1795. Min Act: -0.0000

Data Index: 572673 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1015837 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.1507. Min Act: -0.0000

Data Index: 670290 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1075842 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.1289. Min Act: -0.0000

Data Index: 412468 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.0867. Min Act: -0.0000

Data Index: 53813 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.0988. Min Act: 0.0001

Data Index: 1312217 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.0756. Min Act: -0.0000

Data Index: 628884 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.0550. Min Act: 0.0001

Data Index: 308922 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.5149. Min Range: -1.5149

Max Act: 1.0610. Min Act: -0.0000

Data Index: 958230 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1028405 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.9834. Min Act: -0.0000

Data Index: 912936 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.9892. Min Act: -0.0000

Data Index: 602644 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1050507 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1313137 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1061178 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.9466. Min Act: 0.0001

Data Index: 1282262 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.5149. Min Range: -1.5149

Max Act: 0.8898. Min Act: -0.0000

Data Index: 206070 (C4 (Web Text))

Max Activating Token Index: 612