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

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

Neuron 2634 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1265431 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1867. Min Act: -0.0000

Data Index: 789723 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1831. Min Act: -0.0000

Data Index: 397138 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.2010. Min Act: -0.0000

Data Index: 638661 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1737. Min Act: -0.0000

Data Index: 363671 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1000791 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1046239 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1662. Min Act: -0.0000

Data Index: 816907 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1799. Min Act: -0.0000

Data Index: 272734 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1277426 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1099528 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1728. Min Act: -0.0000

Data Index: 650168 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1584. Min Act: -0.0000

Data Index: 95701 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1696. Min Act: -0.0000

Data Index: 809475 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1574. Min Act: -0.0000

Data Index: 477583 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1435041 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1331. Min Act: -0.0000

Data Index: 256586 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1087278 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1229. Min Act: -0.0000

Data Index: 263482 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1318161 (C4 (Web Text))

Max Activating Token Index: 217