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

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

Neuron 763 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2781. Min Act: -0.0000

Data Index: 493846 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2057. Min Act: -0.0000

Data Index: 516217 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1178112 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1722. Min Act: -0.0000

Data Index: 500669 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1581. Min Act: -0.0000

Data Index: 427622 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1557. Min Act: -0.0000

Data Index: 610663 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1480. Min Act: -0.0000

Data Index: 447153 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1709. Min Act: -0.0000

Data Index: 787970 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1717. Min Act: -0.0000

Data Index: 950626 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1643. Min Act: -0.0000

Data Index: 907777 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1531. Min Act: -0.0000

Data Index: 432467 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1176886 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1197634 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1265858 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1866. Min Act: -0.0000

Data Index: 724988 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1601. Min Act: -0.0000

Data Index: 694693 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1514. Min Act: -0.0000

Data Index: 616264 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1101183 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1300819 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1492948 (Python Code)

Max Activating Token Index: 565