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

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

Neuron 3916 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: 2.1573. Min Range: -2.1573

Max Act: 2.1573. Min Act: -0.0000

Data Index: 866597 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.7189. Min Act: -0.0000

Data Index: 278632 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.9298. Min Act: -0.0000

Data Index: 7934 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.8344. Min Act: -0.0000

Data Index: 366379 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.1482. Min Act: -0.0000

Data Index: 828986 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0051. Min Act: -0.0000

Data Index: 749600 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0897. Min Act: -0.0000

Data Index: 772951 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.1115. Min Act: -0.0000

Data Index: 727468 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0198. Min Act: -0.0000

Data Index: 966172 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0999. Min Act: -0.0000

Data Index: 582656 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0023. Min Act: -0.0000

Data Index: 564902 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0578. Min Act: -0.0000

Data Index: 13282 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0052. Min Act: -0.0000

Data Index: 574815 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0278. Min Act: -0.0000

Data Index: 958437 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 2.1573. Min Range: -2.1573

Max Act: 0.9619. Min Act: -0.0000

Data Index: 429552 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.1573. Min Range: -2.1573

Max Act: 0.9631. Min Act: -0.0000

Data Index: 1255083 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 2.1573. Min Range: -2.1573

Max Act: 0.9798. Min Act: -0.0000

Data Index: 977603 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0601. Min Act: -0.0000

Data Index: 247670 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 2.1573. Min Range: -2.1573

Max Act: 1.0436. Min Act: -0.0000

Data Index: 823459 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 2.1573. Min Range: -2.1573

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1034525 (C4 (Web Text))

Max Activating Token Index: 760