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

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

Neuron 726 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1880. Min Range: -7.1880

Max Act: 6.6044. Min Act: -0.0000

Data Index: 123292 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 7.1880. Min Range: -7.1880

Max Act: 7.1880. Min Act: -0.0000

Data Index: 643374 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 7.1880. Min Range: -7.1880

Max Act: 6.7017. Min Act: -0.0000

Data Index: 854626 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.9068. Min Act: -0.0000

Data Index: 44122 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.8999. Min Act: -0.0000

Data Index: 515457 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 7.1880. Min Range: -7.1880

Max Act: 6.3867. Min Act: -0.0000

Data Index: 949004 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.9561. Min Act: -0.0000

Data Index: 5329 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.1417. Min Act: -0.0000

Data Index: 101476 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.6363. Min Act: -0.0000

Data Index: 606429 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.7221. Min Act: -0.0000

Data Index: 1358599 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.5245. Min Act: -0.0000

Data Index: 337788 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.3334. Min Act: -0.0000

Data Index: 446124 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.4876. Min Act: -0.0000

Data Index: 243734 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.2857. Min Act: -0.0000

Data Index: 1319538 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.2670. Min Act: -0.0000

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.6324. Min Act: -0.0000

Data Index: 286455 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.4267. Min Act: -0.0000

Data Index: 962988 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.4804. Min Act: -0.0000

Data Index: 1207440 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.1301. Min Act: -0.0000

Data Index: 713834 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 7.1880. Min Range: -7.1880

Max Act: 5.4711. Min Act: -0.0000

Data Index: 1039838 (C4 (Web Text))

Max Activating Token Index: 593