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

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

Neuron 788 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1316694 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2471. Min Act: -0.0000

Data Index: 819240 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2461. Min Act: -0.0000

Data Index: 968287 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2284. Min Act: -0.0000

Data Index: 741799 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1240939 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2317. Min Act: -0.0000

Data Index: 846404 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2296. Min Act: -0.0000

Data Index: 604819 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1000453 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2098. Min Act: -0.0000

Data Index: 192239 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1999. Min Act: -0.0000

Data Index: 92586 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1339298 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2020. Min Act: -0.0000

Data Index: 337333 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1856. Min Act: -0.0000

Data Index: 110235 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1156760 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1354455 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1257688 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.2063. Min Act: -0.0000

Data Index: 228770 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1784. Min Act: -0.0000

Data Index: 59533 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1851. Min Act: -0.0000

Data Index: 89994 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.2568. Min Range: -0.2568

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1089995 (C4 (Web Text))

Max Activating Token Index: 361