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

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

Neuron 5448 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: 0.3065. Min Range: -0.3065

Max Act: 0.3065. Min Act: -0.0000

Data Index: 180390 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2403. Min Act: -0.0000

Data Index: 614095 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2167. Min Act: -0.0000

Data Index: 106839 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2098. Min Act: -0.0000

Data Index: 688902 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2108. Min Act: -0.0000

Data Index: 131531 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1098016 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1921. Min Act: -0.0000

Data Index: 706175 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1782. Min Act: -0.0000

Data Index: 689702 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1832. Min Act: -0.0000

Data Index: 359261 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1757. Min Act: -0.0000

Data Index: 662592 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1217791 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1684. Min Act: -0.0000

Data Index: 694674 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1618. Min Act: -0.0000

Data Index: 751053 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1728. Min Act: -0.0000

Data Index: 1290004 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1666. Min Act: -0.0000

Data Index: 783326 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1629. Min Act: -0.0000

Data Index: 272942 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1626. Min Act: -0.0000

Data Index: 410083 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1558. Min Act: -0.0000

Data Index: 118590 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1158073 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.1587. Min Act: -0.0000

Data Index: 377195 (C4 (Web Text))

Max Activating Token Index: 794