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

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

Neuron 507 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2096. Min Act: -0.0000

Data Index: 911655 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2252. Min Act: -0.0000

Data Index: 319839 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2201. Min Act: -0.0000

Data Index: 806361 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2187. Min Act: -0.0000

Data Index: 213723 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2018. Min Act: -0.0000

Data Index: 835617 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2006. Min Act: -0.0000

Data Index: 291431 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1090500 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1177388 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1193319 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1967. Min Act: -0.0000

Data Index: 280860 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1277394 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1950. Min Act: -0.0000

Data Index: 837887 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1936. Min Act: -0.0000

Data Index: 830906 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1859. Min Act: -0.0000

Data Index: 97152 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1851. Min Act: -0.0000

Data Index: 285552 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1880. Min Act: -0.0000

Data Index: 577379 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1273338 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1848. Min Act: -0.0000

Data Index: 868601 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1839. Min Act: -0.0000

Data Index: 248193 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1742. Min Act: -0.0000

Data Index: 126542 (C4 (Web Text))

Max Activating Token Index: 826