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

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

Neuron 4404 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1114895 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2340. Min Act: -0.0000

Data Index: 286510 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2367. Min Act: -0.0000

Data Index: 76296 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2413. Min Act: -0.0000

Data Index: 722622 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2141. Min Act: -0.0000

Data Index: 571429 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2025. Min Act: -0.0000

Data Index: 17281 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1868. Min Act: -0.0000

Data Index: 385949 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1931. Min Act: -0.0000

Data Index: 587965 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2005. Min Act: -0.0000

Data Index: 292921 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1238262 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1062250 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.2081. Min Act: -0.0000

Data Index: 461392 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1991. Min Act: -0.0000

Data Index: 113875 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1257484 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1884. Min Act: -0.0000

Data Index: 903319 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1908. Min Act: -0.0000

Data Index: 183122 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1179332 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1165249 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1877. Min Act: -0.0000

Data Index: 164022 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.2789. Min Range: -0.2789

Max Act: 0.1804. Min Act: -0.0000

Data Index: 726834 (C4 (Web Text))

Max Activating Token Index: 470