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

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

Neuron 4739 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: 3.3297. Min Range: -3.3297

Max Act: 3.0954. Min Act: -0.0000

Data Index: 7402 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.9859. Min Act: -0.0000

Data Index: 680560 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.3297. Min Act: -0.0000

Data Index: 88716 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 3.3297. Min Range: -3.3297

Max Act: 3.2481. Min Act: -0.0000

Data Index: 533589 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.8018. Min Act: -0.0000

Data Index: 1155896 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.9350. Min Act: -0.0000

Data Index: 523498 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.8546. Min Act: -0.0000

Data Index: 390506 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.6977. Min Act: -0.0000

Data Index: 556348 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.7941. Min Act: -0.0000

Data Index: 192865 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.7732. Min Act: -0.0000

Data Index: 422657 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.7104. Min Act: -0.0000

Data Index: 1250414 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.6989. Min Act: -0.0000

Data Index: 494029 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.5465. Min Act: -0.0000

Data Index: 671108 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.6460. Min Act: -0.0000

Data Index: 212746 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.6349. Min Act: -0.0000

Data Index: 819887 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.6242. Min Act: -0.0000

Data Index: 999278 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.5723. Min Act: -0.0000

Data Index: 534634 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.5393. Min Act: -0.0000

Data Index: 262910 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.4181. Min Act: -0.0000

Data Index: 1324716 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 3.3297. Min Range: -3.3297

Max Act: 2.6767. Min Act: -0.0000

Data Index: 588819 (C4 (Web Text))

Max Activating Token Index: 139