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

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

Neuron 251 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.2092. Min Act: -0.0000

Data Index: 521988 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.2100. Min Act: -0.0000

Data Index: 398203 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1350416 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1090271 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1737. Min Act: -0.0000

Data Index: 644325 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1668. Min Act: -0.0000

Data Index: 753022 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1702. Min Act: -0.0000

Data Index: 373659 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1246808 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1632. Min Act: -0.0000

Data Index: 668666 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1664. Min Act: -0.0000

Data Index: 177828 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1618. Min Act: -0.0000

Data Index: 777765 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1192136 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1582. Min Act: -0.0000

Data Index: 785177 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1661. Min Act: -0.0000

Data Index: 865887 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1200680 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1559. Min Act: -0.0000

Data Index: 678025 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1599. Min Act: -0.0000

Data Index: 102797 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1558. Min Act: 0.0000

Data Index: 226701 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1198550 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1176367 (C4 (Web Text))

Max Activating Token Index: 231