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

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

Neuron 2726 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0002

Data Index: 52174 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0671. Min Act: -0.0003

Data Index: 631995 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1322178 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0655. Min Act: -0.0003

Data Index: 921759 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0629. Min Act: -0.0003

Data Index: 544949 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1307693 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0602. Min Act: -0.0003

Data Index: 24964 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0583. Min Act: -0.0003

Data Index: 649929 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0554. Min Act: -0.0003

Data Index: 636865 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1159463 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0594. Min Act: -0.0002

Data Index: 169283 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0548. Min Act: -0.0002

Data Index: 884757 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0570. Min Act: -0.0003

Data Index: 827496 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0558. Min Act: -0.0003

Data Index: 517021 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0561. Min Act: -0.0002

Data Index: 547082 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0556. Min Act: -0.0003

Data Index: 424386 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0553. Min Act: -0.0003

Data Index: 659198 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0556. Min Act: -0.0003

Data Index: 388046 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1168182 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0554. Min Act: -0.0003

Data Index: 24460 (C4 (Web Text))

Max Activating Token Index: 544