Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5880 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1139914 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1143289 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.2164. Min Act: -0.0000

Data Index: 700527 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1863. Min Act: -0.0000

Data Index: 1282322 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1307354 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1149856 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.2250. Min Act: -0.0000

Data Index: 1235930 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0914. Min Act: -0.0000

Data Index: 164778 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1231758 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0288. Min Act: -0.0000

Data Index: 971827 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1299858 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0214. Min Act: -0.0000

Data Index: 158497 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0449. Min Act: -0.0000

Data Index: 800651 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 1.5915. Min Range: -1.5915

Max Act: 1.0423. Min Act: -0.0000

Data Index: 970312 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.9204. Min Act: -0.0000

Data Index: 16637 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.8982. Min Act: -0.0000

Data Index: 511264 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.9062. Min Act: -0.0000

Data Index: 506987 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.8950. Min Act: -0.0000

Data Index: 555252 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.8637. Min Act: -0.0000

Data Index: 872270 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.5915. Min Range: -1.5915

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1348927 (C4 (Web Text))

Max Activating Token Index: 875