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

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

Neuron 3455 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.2064. Min Act: -0.0001

Data Index: 1345622 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1433198 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1989. Min Act: -0.0001

Data Index: 755241 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1471368 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1015374 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1992. Min Act: -0.0001

Data Index: 674226 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1983. Min Act: -0.0001

Data Index: 330388 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1849. Min Act: -0.0001

Data Index: 591349 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1359588 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1029684 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1809. Min Act: -0.0001

Data Index: 778304 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1427522 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1804. Min Act: -0.0001

Data Index: 918817 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1605634 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1611. Min Act: -0.0001

Data Index: 153588 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1738. Min Act: -0.0001

Data Index: 320527 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1722. Min Act: -0.0001

Data Index: 588712 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1713. Min Act: -0.0001

Data Index: 1650895 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1538388 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 0.2217. Min Range: -0.2217

Max Act: 0.1432. Min Act: -0.0001

Data Index: 475928 (C4 (Web Text))

Max Activating Token Index: 212