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

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

Neuron 5833 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.1240. Min Range: -11.1240

Max Act: 11.1240. Min Act: -0.0000

Data Index: 500055 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.6020. Min Act: -0.0000

Data Index: 743565 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.5343. Min Act: -0.0000

Data Index: 324975 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.6595. Min Act: -0.0000

Data Index: 376734 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.1849. Min Act: -0.0000

Data Index: 1289471 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.1852. Min Act: -0.0000

Data Index: 1012368 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.8813. Min Act: -0.0000

Data Index: 562806 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.2693. Min Act: -0.0000

Data Index: 655382 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.1022. Min Act: -0.0000

Data Index: 873058 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.0465. Min Act: -0.0000

Data Index: 952109 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.5418. Min Act: -0.0000

Data Index: 507563 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.4869. Min Act: -0.0000

Data Index: 219016 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.1201. Min Act: -0.0000

Data Index: 1283340 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 11.1240. Min Range: -11.1240

Max Act: 10.2057. Min Act: -0.0000

Data Index: 1194495 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.6498. Min Act: 0.0005

Data Index: 881286 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.4708. Min Act: 0.0000

Data Index: 837360 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.4569. Min Act: -0.0000

Data Index: 227037 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.2439. Min Act: -0.0000

Data Index: 797117 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.3482. Min Act: 0.0005

Data Index: 164886 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 11.1240. Min Range: -11.1240

Max Act: 9.5807. Min Act: -0.0000

Data Index: 238920 (C4 (Web Text))

Max Activating Token Index: 780