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

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

Neuron 3886 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: 2.1914. Min Range: -2.1914

Max Act: 2.1603. Min Act: -0.0000

Data Index: 516063 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 2.1914. Min Range: -2.1914

Max Act: 2.1914. Min Act: -0.0000

Data Index: 898408 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 2.1914. Min Range: -2.1914

Max Act: 2.1864. Min Act: -0.0000

Data Index: 39839 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.9287. Min Act: -0.0000

Data Index: 439193 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.8881. Min Act: -0.0000

Data Index: 1315541 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 2.1914. Min Range: -2.1914

Max Act: 2.0326. Min Act: -0.0000

Data Index: 1091953 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.8971. Min Act: -0.0000

Data Index: 74162 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7498. Min Act: -0.0000

Data Index: 472840 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7417. Min Act: -0.0000

Data Index: 924436 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.8265. Min Act: -0.0000

Data Index: 397573 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7938. Min Act: -0.0000

Data Index: 212489 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7903. Min Act: -0.0000

Data Index: 319179 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7923. Min Act: -0.0000

Data Index: 549356 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7361. Min Act: -0.0000

Data Index: 753804 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7292. Min Act: -0.0000

Data Index: 1160569 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.6996. Min Act: -0.0000

Data Index: 506304 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.6758. Min Act: -0.0000

Data Index: 1213766 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.7475. Min Act: -0.0000

Data Index: 506886 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.6714. Min Act: -0.0000

Data Index: 551623 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 2.1914. Min Range: -2.1914

Max Act: 1.6306. Min Act: -0.0000

Data Index: 980885 (C4 (Web Text))

Max Activating Token Index: 674