Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3569 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1478. Min Range: -1.1478

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1282019 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9830. Min Act: -0.0000

Data Index: 579922 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1125485 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1220197 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8753. Min Act: -0.0000

Data Index: 223173 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8662. Min Act: -0.0000

Data Index: 698826 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8251. Min Act: -0.0000

Data Index: 742353 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7757. Min Act: -0.0000

Data Index: 108049 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1014039 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8014. Min Act: -0.0000

Data Index: 59686 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7904. Min Act: -0.0000

Data Index: 468468 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.8059. Min Act: -0.0000

Data Index: 5574 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7721. Min Act: -0.0000

Data Index: 167711 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1243583 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7541. Min Act: -0.0000

Data Index: 781587 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7319. Min Act: -0.0000

Data Index: 13626 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7632. Min Act: -0.0000

Data Index: 463587 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.6866. Min Act: -0.0000

Data Index: 489010 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1081737 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.1478. Min Range: -1.1478

Max Act: 0.6936. Min Act: -0.0000

Data Index: 23201 (C4 (Web Text))

Max Activating Token Index: 285