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

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

Neuron 3307 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.3086. Min Act: -0.0000

Data Index: 593944 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2573. Min Act: -0.0000

Data Index: 379654 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2262. Min Act: -0.0000

Data Index: 657094 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1091790 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2097. Min Act: -0.0000

Data Index: 990510 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1759. Min Act: -0.0000

Data Index: 543377 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1816. Min Act: -0.0000

Data Index: 773759 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.2013. Min Act: -0.0000

Data Index: 69136 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1826. Min Act: -0.0000

Data Index: 547120 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1706. Min Act: -0.0000

Data Index: 560171 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1732. Min Act: -0.0000

Data Index: 60771 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1722. Min Act: -0.0000

Data Index: 964890 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1291599 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1772. Min Act: -0.0000

Data Index: 547636 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1728. Min Act: -0.0000

Data Index: 670549 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1617. Min Act: -0.0000

Data Index: 453465 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1481. Min Act: -0.0000

Data Index: 824576 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1754. Min Act: -0.0000

Data Index: 987404 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1260077 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.3086. Min Range: -0.3086

Max Act: 0.1596. Min Act: -0.0000

Data Index: 1244091 (C4 (Web Text))

Max Activating Token Index: 342