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

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

Neuron 4881 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0002

Data Index: 432829 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0002

Data Index: 240629 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0910. Min Act: -0.0002

Data Index: 839462 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0885. Min Act: -0.0002

Data Index: 257688 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0850. Min Act: -0.0002

Data Index: 237398 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1280987 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1036333 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0752. Min Act: -0.0002

Data Index: 33044 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0792. Min Act: -0.0002

Data Index: 383505 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0811. Min Act: -0.0002

Data Index: 718255 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1144645 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0767. Min Act: -0.0002

Data Index: 706800 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1205476 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0765. Min Act: -0.0002

Data Index: 761259 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0843. Min Act: -0.0002

Data Index: 263092 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1353065 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1048308 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0719. Min Act: -0.0002

Data Index: 896049 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1023552 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0699. Min Act: -0.0002

Data Index: 512154 (C4 (Web Text))

Max Activating Token Index: 101