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

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

Neuron 5752 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: 0.8430. Min Range: -0.8430

Max Act: 0.8430. Min Act: -0.0000

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1647649 (Python Code)

Max Activating Token Index: 1012

Text #2

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6486. Min Act: -0.0000

Data Index: 758610 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6190. Min Act: -0.0000

Data Index: 269521 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5625. Min Act: -0.0000

Data Index: 331838 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5651. Min Act: -0.0000

Data Index: 707593 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5774. Min Act: -0.0000

Data Index: 721244 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1276994 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.5028. Min Act: -0.0000

Data Index: 312171 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1224348 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4713. Min Act: -0.0000

Data Index: 10496 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1039535 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1152369 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1268345 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1444411 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.3812. Min Act: -0.0000

Data Index: 545392 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.3968. Min Act: -0.0000

Data Index: 174197 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4243. Min Act: -0.0000

Data Index: 364221 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1523566 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 0.8430. Min Range: -0.8430

Max Act: 0.3870. Min Act: -0.0000

Data Index: 506843 (C4 (Web Text))

Max Activating Token Index: 419