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

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

Neuron 537 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1479233 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1022. Min Act: -0.0000

Data Index: 958312 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1588943 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1597958 (Python Code)

Max Activating Token Index: 799

Text #4

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1535117 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1638852 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1369177 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1453167 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1036. Min Act: -0.0000

Data Index: 604858 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1440109 (Python Code)

Max Activating Token Index: 268

Text #10

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1634310 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1578524 (Python Code)

Max Activating Token Index: 657

Text #12

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1444518 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1405222 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1059377 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1390330 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1072440 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1095466 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1420174 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1493828 (Python Code)

Max Activating Token Index: 596