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

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

Neuron 4941 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2419. Min Act: -0.0000

Data Index: 420250 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2183. Min Act: -0.0000

Data Index: 348772 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2055. Min Act: -0.0000

Data Index: 990779 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2030. Min Act: -0.0000

Data Index: 678294 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2006. Min Act: -0.0000

Data Index: 968238 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1944. Min Act: -0.0000

Data Index: 193378 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1922. Min Act: -0.0000

Data Index: 401194 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1047741 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1797. Min Act: -0.0000

Data Index: 996009 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1990. Min Act: -0.0000

Data Index: 692660 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1759. Min Act: -0.0000

Data Index: 647493 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1047001 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1891. Min Act: -0.0000

Data Index: 945081 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1118916 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1846. Min Act: -0.0000

Data Index: 658582 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1357414 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1824. Min Act: -0.0000

Data Index: 604337 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1772. Min Act: -0.0000

Data Index: 344824 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1263488 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.2419. Min Range: -0.2419

Max Act: 0.2002. Min Act: -0.0000

Data Index: 74267 (C4 (Web Text))

Max Activating Token Index: 44