Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2006 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1049. Min Act: -0.0001

Data Index: 800875 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1033. Min Act: -0.0001

Data Index: 659490 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0763. Min Act: -0.0001

Data Index: 280152 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0727. Min Act: -0.0001

Data Index: 148959 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0785. Min Act: -0.0001

Data Index: 416617 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0730. Min Act: -0.0001

Data Index: 652041 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0799. Min Act: -0.0001

Data Index: 684623 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0737. Min Act: -0.0001

Data Index: 567977 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0743. Min Act: -0.0001

Data Index: 129935 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0705. Min Act: -0.0001

Data Index: 796159 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1166391 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1194203 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0741. Min Act: -0.0001

Data Index: 161284 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1232853 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0708. Min Act: -0.0001

Data Index: 232391 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0639. Min Act: -0.0001

Data Index: 992495 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1092415 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0670. Min Act: -0.0001

Data Index: 449244 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0683. Min Act: -0.0001

Data Index: 269084 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1208240 (C4 (Web Text))

Max Activating Token Index: 826