Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4665 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1355177 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.3036. Min Act: -0.0000

Data Index: 188138 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.2492. Min Act: -0.0000

Data Index: 3608 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1997. Min Act: -0.0000

Data Index: 296966 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1040852 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0083. Min Act: -0.0000

Data Index: 38330 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1412. Min Act: -0.0000

Data Index: 18929 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1684. Min Act: -0.0000

Data Index: 852863 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1554. Min Act: -0.0000

Data Index: 581514 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1007. Min Act: -0.0000

Data Index: 513369 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1083708 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0582. Min Act: -0.0000

Data Index: 266822 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1144. Min Act: -0.0000

Data Index: 418683 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1230. Min Act: -0.0000

Data Index: 760554 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0913. Min Act: -0.0000

Data Index: 508587 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0317. Min Act: -0.0000

Data Index: 200213 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1139732 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1271386 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1032042 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0476. Min Act: -0.0000

Data Index: 521433 (C4 (Web Text))

Max Activating Token Index: 199