Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1987 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1854. Min Act: -0.0002

Data Index: 560558 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1766. Min Act: -0.0002

Data Index: 1228835 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1792. Min Act: -0.0002

Data Index: 875611 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1846. Min Act: -0.0002

Data Index: 805854 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1803. Min Act: -0.0002

Data Index: 111097 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1717. Min Act: -0.0002

Data Index: 315277 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1661. Min Act: -0.0002

Data Index: 644850 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1538. Min Act: -0.0002

Data Index: 203218 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1690. Min Act: -0.0002

Data Index: 979066 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1637. Min Act: -0.0002

Data Index: 207168 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1751. Min Act: -0.0002

Data Index: 123547 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1627. Min Act: -0.0002

Data Index: 73484 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1733. Min Act: -0.0002

Data Index: 704667 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1644. Min Act: -0.0002

Data Index: 273825 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1675. Min Act: -0.0002

Data Index: 1005116 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1583. Min Act: -0.0002

Data Index: 138492 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1559. Min Act: -0.0002

Data Index: 935947 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1690. Min Act: -0.0002

Data Index: 7456 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1545. Min Act: -0.0002

Data Index: 481027 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1854. Min Range: -0.1854

Max Act: 0.1592. Min Act: -0.0002

Data Index: 850482 (C4 (Web Text))

Max Activating Token Index: 696