Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1091 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2189. Min Act: -0.0005

Data Index: 1203021 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2007. Min Act: -0.0005

Data Index: 887999 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.2012. Min Act: -0.0005

Data Index: 590603 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1849. Min Act: -0.0005

Data Index: 1267563 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1967. Min Act: -0.0005

Data Index: 50304 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1953. Min Act: -0.0005

Data Index: 462505 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1941. Min Act: -0.0005

Data Index: 1225780 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1933. Min Act: -0.0005

Data Index: 1029027 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1920. Min Act: -0.0005

Data Index: 956910 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1896. Min Act: -0.0005

Data Index: 112963 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1870. Min Act: -0.0005

Data Index: 247208 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1783. Min Act: -0.0005

Data Index: 569850 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1992. Min Act: -0.0005

Data Index: 755086 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1919. Min Act: -0.0005

Data Index: 781933 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1721. Min Act: -0.0005

Data Index: 980099 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1915. Min Act: -0.0005

Data Index: 342210 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1908. Min Act: -0.0005

Data Index: 641897 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1702. Min Act: -0.0005

Data Index: 331654 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1753. Min Act: -0.0005

Data Index: 689989 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.2189. Min Range: -0.2189

Max Act: 0.1882. Min Act: -0.0005

Data Index: 325740 (C4 (Web Text))

Max Activating Token Index: 995