Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1842 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2837. Min Act: -0.0000

Data Index: 277818 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1243108 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2146. Min Act: -0.0000

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1134311 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.2049. Min Act: -0.0000

Data Index: 941320 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1253583 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1357836 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1692. Min Act: -0.0000

Data Index: 831781 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1960. Min Act: -0.0000

Data Index: 372826 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1155422 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1696. Min Act: -0.0000

Data Index: 129974 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1184048 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1814. Min Act: -0.0000

Data Index: 237758 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1670. Min Act: -0.0000

Data Index: 879041 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1619. Min Act: -0.0000

Data Index: 739917 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1001761 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1721. Min Act: -0.0000

Data Index: 570925 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1643. Min Act: -0.0000

Data Index: 139192 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1584. Min Act: -0.0000

Data Index: 285743 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.2837. Min Range: -0.2837

Max Act: 0.1571. Min Act: -0.0000

Data Index: 83615 (C4 (Web Text))

Max Activating Token Index: 737