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

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

Neuron 804 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: 4.1495. Min Range: -4.1495

Max Act: 4.1495. Min Act: -0.0000

Data Index: 236399 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 4.1495. Min Range: -4.1495

Max Act: 4.0735. Min Act: -0.0000

Data Index: 590142 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.6715. Min Act: -0.0000

Data Index: 36546 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.7629. Min Act: -0.0000

Data Index: 1068182 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.4117. Min Act: -0.0000

Data Index: 335414 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.5587. Min Act: -0.0000

Data Index: 257944 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.2891. Min Act: -0.0000

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.3827. Min Act: -0.0000

Data Index: 788263 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.1399. Min Act: -0.0000

Data Index: 124653 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.9917. Min Act: -0.0000

Data Index: 200401 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.0449. Min Act: -0.0000

Data Index: 1090267 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 4.1495. Min Range: -4.1495

Max Act: 3.0055. Min Act: -0.0000

Data Index: 336259 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.6465. Min Act: -0.0000

Data Index: 565444 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.9002. Min Act: -0.0000

Data Index: 298375 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.8521. Min Act: -0.0000

Data Index: 698489 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.8123. Min Act: -0.0000

Data Index: 321838 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.9359. Min Act: -0.0000

Data Index: 912258 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.6371. Min Act: -0.0000

Data Index: 32873 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.7447. Min Act: -0.0000

Data Index: 1032262 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 4.1495. Min Range: -4.1495

Max Act: 2.6153. Min Act: -0.0000

Data Index: 1128458 (C4 (Web Text))

Max Activating Token Index: 153