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

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

Neuron 577 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.8110. Min Act: -0.0001

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.7361. Min Act: -0.0001

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.7977. Min Act: -0.0001

Data Index: 785698 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.8534. Min Act: -0.0001

Data Index: 1262392 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.9023. Min Act: -0.0001

Data Index: 806619 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.4133. Min Act: -0.0001

Data Index: 113474 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.2007. Min Act: -0.0001

Data Index: 680827 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.1282. Min Act: -0.0001

Data Index: 498341 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.2498. Min Act: -0.0001

Data Index: 1196312 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.0850. Min Act: -0.0001

Data Index: 592721 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.1465. Min Act: -0.0001

Data Index: 530061 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.0526. Min Act: -0.0001

Data Index: 822020 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.0378. Min Act: -0.0001

Data Index: 1002017 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.0375. Min Act: -0.0001

Data Index: 644330 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.0315. Min Act: -0.0001

Data Index: 1218980 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 1.9023. Min Range: -1.9023

Max Act: 0.9439. Min Act: -0.0001

Data Index: 864178 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.0353. Min Act: -0.0001

Data Index: 1039786 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.9023. Min Range: -1.9023

Max Act: 0.9092. Min Act: -0.0001

Data Index: 499142 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 1.9023. Min Range: -1.9023

Max Act: 0.9617. Min Act: -0.0001

Data Index: 1202829 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 1.9023. Min Range: -1.9023

Max Act: 1.0515. Min Act: -0.0001

Data Index: 753179 (C4 (Web Text))

Max Activating Token Index: 847