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

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

Neuron 1925 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1896. Min Range: -2.1896

Max Act: 2.1896. Min Act: -0.0000

Data Index: 1323270 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 2.1896. Min Range: -2.1896

Max Act: 2.0491. Min Act: -0.0000

Data Index: 336117 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.9746. Min Act: -0.0000

Data Index: 346135 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.7801. Min Act: -0.0000

Data Index: 1178752 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.8483. Min Act: -0.0000

Data Index: 862206 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.7430. Min Act: -0.0000

Data Index: 838880 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.8408. Min Act: -0.0000

Data Index: 316265 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.8009. Min Act: -0.0000

Data Index: 107878 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.7703. Min Act: -0.0000

Data Index: 452206 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.7280. Min Act: -0.0000

Data Index: 487295 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1063863 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.7045. Min Act: -0.0000

Data Index: 389272 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.6812. Min Act: -0.0000

Data Index: 351265 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.6804. Min Act: -0.0000

Data Index: 1316274 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.6493. Min Act: -0.0000

Data Index: 37053 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.6347. Min Act: -0.0000

Data Index: 1197264 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.6260. Min Act: -0.0000

Data Index: 781258 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.6194. Min Act: -0.0000

Data Index: 752801 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.7049. Min Act: -0.0000

Data Index: 82694 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 2.1896. Min Range: -2.1896

Max Act: 1.6072. Min Act: -0.0000

Data Index: 71150 (C4 (Web Text))

Max Activating Token Index: 225