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

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

Neuron 5083 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: 0.2312. Min Range: -0.2312

Max Act: 0.1960. Min Act: -0.0001

Data Index: 723752 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1984. Min Act: -0.0001

Data Index: 991536 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2312. Min Act: -0.0001

Data Index: 634380 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2003. Min Act: -0.0001

Data Index: 926034 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1920. Min Act: -0.0001

Data Index: 474462 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.2032. Min Act: -0.0001

Data Index: 374409 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1121027 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1860. Min Act: -0.0001

Data Index: 148929 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1049981 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1851. Min Act: -0.0001

Data Index: 896944 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1838. Min Act: -0.0001

Data Index: 1321013 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1332418 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1767. Min Act: -0.0001

Data Index: 752539 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1851. Min Act: -0.0001

Data Index: 16711 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1659. Min Act: -0.0001

Data Index: 897056 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1034114 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1659. Min Act: -0.0001

Data Index: 600559 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1834. Min Act: -0.0001

Data Index: 504528 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1956. Min Act: -0.0001

Data Index: 247481 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.2312. Min Range: -0.2312

Max Act: 0.1756. Min Act: -0.0001

Data Index: 789252 (C4 (Web Text))

Max Activating Token Index: 517