Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2231. Min Act: -0.0000

Data Index: 229149 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1290311 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2169. Min Act: -0.0000

Data Index: 996162 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2029. Min Act: -0.0001

Data Index: 208244 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2212. Min Act: -0.0001

Data Index: 183005 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2021. Min Act: -0.0001

Data Index: 4370 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2136. Min Act: -0.0000

Data Index: 310129 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1992. Min Act: -0.0001

Data Index: 605807 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1925. Min Act: -0.0000

Data Index: 168727 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1962. Min Act: -0.0000

Data Index: 772159 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1013252 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1914. Min Act: -0.0001

Data Index: 162918 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2050. Min Act: -0.0001

Data Index: 330707 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1627. Min Act: -0.0001

Data Index: 814374 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1079389 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1016020 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1029870 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1837. Min Act: -0.0000

Data Index: 599715 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1993. Min Act: -0.0001

Data Index: 642505 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1811. Min Act: -0.0001

Data Index: 545439 (C4 (Web Text))

Max Activating Token Index: 469