Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 635 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0797. Min Act: -0.0002

Data Index: 121206 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0827. Min Act: -0.0002

Data Index: 561691 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1315366 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0001

Data Index: 834933 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0824. Min Act: -0.0002

Data Index: 320083 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0738. Min Act: -0.0002

Data Index: 789083 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0763. Min Act: -0.0001

Data Index: 621980 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0736. Min Act: -0.0002

Data Index: 199068 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0741. Min Act: -0.0002

Data Index: 200668 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0745. Min Act: -0.0001

Data Index: 591746 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0639. Min Act: -0.0002

Data Index: 345412 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0735. Min Act: -0.0002

Data Index: 967733 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0739. Min Act: -0.0001

Data Index: 445118 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0743. Min Act: -0.0002

Data Index: 859288 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0689. Min Act: -0.0002

Data Index: 942585 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0686. Min Act: -0.0001

Data Index: 15983 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1223643 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1158240 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0680. Min Act: -0.0002

Data Index: 379301 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0675. Min Act: -0.0002

Data Index: 486908 (C4 (Web Text))

Max Activating Token Index: 786