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

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

Neuron 3825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1929. Min Act: -0.0001

Data Index: 709244 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.2074. Min Act: -0.0001

Data Index: 889409 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1147740 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1134502 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1739. Min Act: -0.0001

Data Index: 283572 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1721. Min Act: -0.0001

Data Index: 638282 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1760. Min Act: -0.0001

Data Index: 1348468 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1641. Min Act: -0.0001

Data Index: 804563 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1813. Min Act: -0.0001

Data Index: 936838 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1784. Min Act: -0.0001

Data Index: 275752 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1818. Min Act: -0.0001

Data Index: 348466 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1717. Min Act: -0.0001

Data Index: 629658 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1702. Min Act: -0.0001

Data Index: 875706 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1707. Min Act: -0.0001

Data Index: 802230 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1154645 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1118346 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1716. Min Act: -0.0001

Data Index: 681477 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1309125 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1301403 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.2074. Min Range: -0.2074

Max Act: 0.1476. Min Act: -0.0001

Data Index: 609363 (C4 (Web Text))

Max Activating Token Index: 186