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

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

Neuron 1672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3517. Min Range: -2.3517

Max Act: 2.3350. Min Act: -0.0000

Data Index: 1447708 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 2.3517. Min Range: -2.3517

Max Act: 2.3517. Min Act: -0.0000

Data Index: 1276780 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.9962. Min Act: -0.0000

Data Index: 505181 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.9982. Min Act: -0.0000

Data Index: 8585 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1147181 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.9281. Min Act: -0.0000

Data Index: 951066 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.9160. Min Act: -0.0000

Data Index: 907850 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.9651. Min Act: -0.0000

Data Index: 854866 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1003852 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.6990. Min Act: -0.0000

Data Index: 524987 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.7595. Min Act: -0.0000

Data Index: 1426007 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.6002. Min Act: -0.0000

Data Index: 137420 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.6412. Min Act: -0.0000

Data Index: 646760 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.8297. Min Act: -0.0000

Data Index: 1020935 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.8131. Min Act: -0.0000

Data Index: 384107 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.7021. Min Act: -0.0000

Data Index: 1221613 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.5911. Min Act: -0.0000

Data Index: 645807 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.6528. Min Act: -0.0000

Data Index: 164467 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.5379. Min Act: -0.0000

Data Index: 399927 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 2.3517. Min Range: -2.3517

Max Act: 1.7035. Min Act: -0.0000

Data Index: 1280715 (C4 (Web Text))

Max Activating Token Index: 718