Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3142 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.2089. Min Act: -0.0000

Data Index: 39572 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1851. Min Act: -0.0000

Data Index: 911278 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1757. Min Act: -0.0001

Data Index: 557758 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1775. Min Act: -0.0000

Data Index: 98869 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1721. Min Act: -0.0000

Data Index: 405143 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1593. Min Act: -0.0000

Data Index: 73914 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1536. Min Act: -0.0000

Data Index: 959963 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1640. Min Act: -0.0000

Data Index: 780840 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1598. Min Act: -0.0000

Data Index: 347847 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1162752 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1529. Min Act: -0.0000

Data Index: 351420 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1520. Min Act: -0.0000

Data Index: 500683 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1559. Min Act: -0.0000

Data Index: 400625 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1243224 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1499. Min Act: -0.0000

Data Index: 183791 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1099477 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1479. Min Act: -0.0001

Data Index: 850412 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1414. Min Act: -0.0000

Data Index: 955081 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1163928 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1389. Min Act: -0.0000

Data Index: 916668 (C4 (Web Text))

Max Activating Token Index: 302