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

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

Neuron 3918 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.7065. Min Act: -0.0000

Data Index: 596889 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.6371. Min Act: -0.0000

Data Index: 539901 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5912. Min Act: -0.0000

Data Index: 506367 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.6386. Min Act: -0.0000

Data Index: 424031 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1109683 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1108468 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5589. Min Act: -0.0000

Data Index: 879524 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5821. Min Act: -0.0000

Data Index: 221884 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5337. Min Act: -0.0000

Data Index: 275442 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5196. Min Act: -0.0000

Data Index: 671641 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5233. Min Act: -0.0000

Data Index: 851524 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5540. Min Act: -0.0000

Data Index: 940208 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5180. Min Act: -0.0000

Data Index: 468629 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.4921. Min Act: -0.0000

Data Index: 446669 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5001. Min Act: -0.0000

Data Index: 357800 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5080. Min Act: -0.0000

Data Index: 281408 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.5067. Min Act: -0.0000

Data Index: 219095 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.4796. Min Act: -0.0000

Data Index: 965440 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1071917 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 0.7065. Min Range: -0.7065

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1032787 (C4 (Web Text))

Max Activating Token Index: 122