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

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

Neuron 2844 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2667. Min Act: -0.0000

Data Index: 311866 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2470. Min Act: -0.0000

Data Index: 438817 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1139961 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1328131 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2150. Min Act: -0.0000

Data Index: 888886 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2079. Min Act: -0.0000

Data Index: 766669 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2125. Min Act: -0.0000

Data Index: 112346 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1125448 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1317897 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1983. Min Act: -0.0000

Data Index: 192319 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1230549 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1213622 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1788. Min Act: -0.0000

Data Index: 113807 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1929. Min Act: -0.0000

Data Index: 414491 (C4 (Web Text))

Max Activating Token Index: 457

Text #14

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1859. Min Act: -0.0000

Data Index: 10096 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1790. Min Act: -0.0000

Data Index: 402770 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1823. Min Act: -0.0000

Data Index: 397394 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1862. Min Act: -0.0000

Data Index: 392323 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1858. Min Act: -0.0000

Data Index: 305289 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.2667. Min Range: -0.2667

Max Act: 0.1655. Min Act: -0.0000

Data Index: 179119 (C4 (Web Text))

Max Activating Token Index: 547