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

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

Neuron 1453 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0001

Data Index: 539841 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1074528 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0779. Min Act: -0.0001

Data Index: 72064 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0647. Min Act: -0.0001

Data Index: 830658 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0717. Min Act: -0.0001

Data Index: 936270 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0713. Min Act: -0.0001

Data Index: 715243 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0710. Min Act: -0.0001

Data Index: 603485 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0674. Min Act: -0.0001

Data Index: 277391 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0647. Min Act: -0.0001

Data Index: 326754 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0616. Min Act: -0.0001

Data Index: 788982 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1232718 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0644. Min Act: -0.0001

Data Index: 402530 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0517. Min Act: -0.0001

Data Index: 265947 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1353762 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1104365 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1013814 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0520. Min Act: -0.0001

Data Index: 364246 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0649. Min Act: -0.0001

Data Index: 706061 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1014764 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0606. Min Act: -0.0001

Data Index: 616433 (C4 (Web Text))

Max Activating Token Index: 665