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

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

Neuron 1963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5073. Min Range: -6.5073

Max Act: 6.5073. Min Act: -0.0000

Data Index: 313523 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 6.5073. Min Range: -6.5073

Max Act: 6.1001. Min Act: -0.0000

Data Index: 968431 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.8148. Min Act: -0.0000

Data Index: 1148955 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.8562. Min Act: -0.0000

Data Index: 1177016 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 6.5073. Min Range: -6.5073

Max Act: 6.0315. Min Act: -0.0000

Data Index: 587711 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.5894. Min Act: -0.0000

Data Index: 104580 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.6936. Min Act: -0.0000

Data Index: 124463 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.4786. Min Act: -0.0000

Data Index: 1318851 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.4364. Min Act: -0.0000

Data Index: 144997 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.3714. Min Act: -0.0000

Data Index: 162464 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 6.5073. Min Range: -6.5073

Max Act: 4.9181. Min Act: -0.0000

Data Index: 154465 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.0065. Min Act: -0.0000

Data Index: 112251 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.2056. Min Act: -0.0000

Data Index: 497014 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.2048. Min Act: -0.0000

Data Index: 1229941 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.1636. Min Act: -0.0000

Data Index: 953281 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 6.5073. Min Range: -6.5073

Max Act: 5.0867. Min Act: -0.0000

Data Index: 166875 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 6.5073. Min Range: -6.5073

Max Act: 4.8751. Min Act: -0.0000

Data Index: 1231199 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 6.5073. Min Range: -6.5073

Max Act: 4.7413. Min Act: -0.0000

Data Index: 212068 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 6.5073. Min Range: -6.5073

Max Act: 4.9436. Min Act: -0.0000

Data Index: 1233968 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 6.5073. Min Range: -6.5073

Max Act: 4.8625. Min Act: -0.0000

Data Index: 1285458 (C4 (Web Text))

Max Activating Token Index: 128