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

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

Neuron 5764 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: 0.2063. Min Range: -0.2063

Max Act: 0.2063. Min Act: -0.0000

Data Index: 417247 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1978. Min Act: -0.0000

Data Index: 708295 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1892. Min Act: -0.0000

Data Index: 69749 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1760. Min Act: -0.0000

Data Index: 206947 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1679. Min Act: -0.0000

Data Index: 802190 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1090366 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1746. Min Act: -0.0000

Data Index: 444847 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1711. Min Act: -0.0000

Data Index: 156349 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1700. Min Act: -0.0000

Data Index: 556721 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1681. Min Act: -0.0000

Data Index: 90199 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1038890 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1725. Min Act: -0.0000

Data Index: 912266 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1597. Min Act: -0.0000

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1591. Min Act: -0.0000

Data Index: 56589 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1234805 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1576. Min Act: -0.0000

Data Index: 560642 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1619. Min Act: -0.0000

Data Index: 160066 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1528. Min Act: -0.0000

Data Index: 470227 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1425. Min Act: -0.0000

Data Index: 324362 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1515. Min Act: -0.0000

Data Index: 563342 (C4 (Web Text))

Max Activating Token Index: 613