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

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

Neuron 829 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2322. Min Act: -0.0000

Data Index: 507010 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2163. Min Act: -0.0001

Data Index: 529858 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2014. Min Act: -0.0001

Data Index: 1117003 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1850. Min Act: -0.0000

Data Index: 85447 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1284561 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1064890 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1896. Min Act: -0.0000

Data Index: 854068 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1205896 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1260696 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1088152 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1820. Min Act: -0.0000

Data Index: 83040 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1026044 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1671. Min Act: -0.0000

Data Index: 273392 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1648. Min Act: -0.0000

Data Index: 312467 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1030834 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1758. Min Act: -0.0001

Data Index: 1161709 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1635. Min Act: -0.0000

Data Index: 134392 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1672. Min Act: -0.0000

Data Index: 464160 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1671. Min Act: -0.0000

Data Index: 9545 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1012090 (C4 (Web Text))

Max Activating Token Index: 725