Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1832 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1758. Min Act: -0.0001

Data Index: 144872 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1760. Min Act: -0.0001

Data Index: 807492 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1767. Min Act: -0.0001

Data Index: 395783 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1674. Min Act: -0.0001

Data Index: 793418 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1300882 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1705. Min Act: -0.0001

Data Index: 380334 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1701. Min Act: -0.0001

Data Index: 951160 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1654. Min Act: -0.0001

Data Index: 602854 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1690. Min Act: -0.0001

Data Index: 629339 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1681. Min Act: -0.0001

Data Index: 425464 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1443968 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1715. Min Act: -0.0001

Data Index: 173307 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1621. Min Act: -0.0001

Data Index: 1196285 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1593. Min Act: -0.0001

Data Index: 503539 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1546. Min Act: -0.0001

Data Index: 112457 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1699. Min Act: -0.0001

Data Index: 337364 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1675. Min Act: -0.0001

Data Index: 29248 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1580. Min Act: -0.0001

Data Index: 154530 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1656. Min Act: -0.0001

Data Index: 970800 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1562. Min Act: -0.0001

Data Index: 472978 (C4 (Web Text))

Max Activating Token Index: 64