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

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

Neuron 4562 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2608. Min Act: -0.0000

Data Index: 330456 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2162. Min Act: -0.0000

Data Index: 206993 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2020. Min Act: -0.0000

Data Index: 338508 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2013. Min Act: -0.0000

Data Index: 350988 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2000. Min Act: -0.0000

Data Index: 862847 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1960. Min Act: -0.0000

Data Index: 206120 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.2053. Min Act: -0.0000

Data Index: 870961 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1911. Min Act: -0.0000

Data Index: 766161 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1961. Min Act: -0.0000

Data Index: 150186 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1941. Min Act: -0.0000

Data Index: 654866 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1915. Min Act: -0.0000

Data Index: 621965 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1774. Min Act: -0.0000

Data Index: 708813 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1751. Min Act: -0.0000

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1716. Min Act: -0.0000

Data Index: 463457 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1300064 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1646. Min Act: -0.0000

Data Index: 318646 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1018152 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1754. Min Act: -0.0000

Data Index: 264736 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1281316 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.2608. Min Range: -0.2608

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1252299 (C4 (Web Text))

Max Activating Token Index: 686