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

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

Neuron 5331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5782. Min Act: -0.0000

Data Index: 995030 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4777. Min Act: -0.0000

Data Index: 937013 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5443. Min Act: -0.0000

Data Index: 74428 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5226. Min Act: -0.0000

Data Index: 814198 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1290700 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5040. Min Act: -0.0000

Data Index: 627858 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.5299. Min Act: -0.0000

Data Index: 972455 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4779. Min Act: -0.0000

Data Index: 377254 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4953. Min Act: -0.0000

Data Index: 85565 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1146044 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4813. Min Act: -0.0001

Data Index: 732768 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1004281 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1260192 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1339949 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4525. Min Act: -0.0000

Data Index: 436293 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4667. Min Act: -0.0000

Data Index: 92936 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4642. Min Act: -0.0000

Data Index: 1351266 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4436. Min Act: -0.0000

Data Index: 149493 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4353. Min Act: -0.0000

Data Index: 147296 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.5782. Min Range: -0.5782

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1322226 (C4 (Web Text))

Max Activating Token Index: 150