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

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

Neuron 3261 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: 2.6032. Min Range: -2.6032

Max Act: 2.5167. Min Act: -0.0000

Data Index: 107453 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.6032. Min Act: -0.0000

Data Index: 953061 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1083163 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.3714. Min Act: -0.0000

Data Index: 769503 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.3222. Min Act: -0.0000

Data Index: 149964 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.4125. Min Act: -0.0000

Data Index: 248612 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.3527. Min Act: -0.0000

Data Index: 1065374 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.0743. Min Act: -0.0000

Data Index: 1090770 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.9142. Min Act: -0.0000

Data Index: 851108 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.0150. Min Act: -0.0000

Data Index: 1245078 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1336536 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 2.6032. Min Range: -2.6032

Max Act: 2.0797. Min Act: -0.0000

Data Index: 139345 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.9688. Min Act: -0.0000

Data Index: 1138456 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.7741. Min Act: -0.0000

Data Index: 279751 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.9776. Min Act: -0.0000

Data Index: 366098 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.8745. Min Act: -0.0000

Data Index: 1242457 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.9558. Min Act: -0.0000

Data Index: 281723 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.9470. Min Act: -0.0000

Data Index: 975623 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.9606. Min Act: -0.0000

Data Index: 353343 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 2.6032. Min Range: -2.6032

Max Act: 1.8293. Min Act: -0.0000

Data Index: 942422 (C4 (Web Text))

Max Activating Token Index: 157