Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1711 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0003

Data Index: 636984 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1970. Min Act: -0.0003

Data Index: 1091524 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1876. Min Act: -0.0003

Data Index: 499976 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1828. Min Act: -0.0003

Data Index: 967918 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1878. Min Act: -0.0003

Data Index: 448052 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1795. Min Act: -0.0004

Data Index: 827868 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1734. Min Act: -0.0003

Data Index: 364113 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1759. Min Act: -0.0002

Data Index: 814107 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1724. Min Act: -0.0003

Data Index: 324779 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1787. Min Act: -0.0003

Data Index: 42531 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1745. Min Act: -0.0003

Data Index: 575741 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1759. Min Act: -0.0003

Data Index: 968993 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1675. Min Act: -0.0004

Data Index: 654305 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1682. Min Act: -0.0003

Data Index: 206898 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1669. Min Act: -0.0003

Data Index: 117950 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1654. Min Act: -0.0004

Data Index: 1195113 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1576. Min Act: -0.0003

Data Index: 366400 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1721. Min Act: -0.0003

Data Index: 979514 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1616. Min Act: -0.0003

Data Index: 1008879 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1660. Min Act: -0.0004

Data Index: 580692 (C4 (Web Text))

Max Activating Token Index: 238