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

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

Neuron 2795 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.7090. Min Act: -0.0001

Data Index: 691885 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.6528. Min Act: -0.0002

Data Index: 578993 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.6383. Min Act: -0.0002

Data Index: 890498 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.6136. Min Act: -0.0002

Data Index: 1322250 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5336. Min Act: -0.0002

Data Index: 94538 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5711. Min Act: -0.0002

Data Index: 536780 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5246. Min Act: -0.0002

Data Index: 504126 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5221. Min Act: -0.0001

Data Index: 583575 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5068. Min Act: -0.0002

Data Index: 4821 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5373. Min Act: -0.0002

Data Index: 37715 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5249. Min Act: -0.0002

Data Index: 1043574 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5567. Min Act: -0.0002

Data Index: 829194 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5090. Min Act: -0.0001

Data Index: 1336697 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.4791. Min Act: -0.0001

Data Index: 1200756 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.4871. Min Act: -0.0002

Data Index: 894839 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5154. Min Act: -0.0001

Data Index: 235764 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.5271. Min Act: -0.0002

Data Index: 1177090 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.4721. Min Act: -0.0002

Data Index: 315073 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.4779. Min Act: -0.0002

Data Index: 948438 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.7090. Min Range: -0.7090

Max Act: 0.4908. Min Act: -0.0002

Data Index: 1074494 (C4 (Web Text))

Max Activating Token Index: 444