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

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

Neuron 3372 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.2167. Min Act: -0.0000

Data Index: 596147 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.2231. Min Act: -0.0001

Data Index: 984974 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1166991 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1203869 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.1798. Min Act: -0.0000

Data Index: 615568 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.1782. Min Act: -0.0000

Data Index: 978662 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.1055. Min Act: -0.0001

Data Index: 578129 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1268088 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0812. Min Act: -0.0000

Data Index: 984302 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1062780 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1309754 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0864. Min Act: -0.0000

Data Index: 152667 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0999. Min Act: -0.0000

Data Index: 614017 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0792. Min Act: -0.0000

Data Index: 819338 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0914. Min Act: -0.0001

Data Index: 437816 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1071988 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0882. Min Act: -0.0000

Data Index: 280944 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0848. Min Act: -0.0000

Data Index: 882189 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0917. Min Act: -0.0000

Data Index: 52064 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.2231. Min Range: -0.2231

Max Act: 0.0706. Min Act: -0.0000

Data Index: 336023 (C4 (Web Text))

Max Activating Token Index: 871