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

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

Neuron 4403 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: 2.1880. Min Range: -2.1880

Max Act: 2.1880. Min Act: -0.0000

Data Index: 544432 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 2.1880. Min Range: -2.1880

Max Act: 2.1180. Min Act: -0.0000

Data Index: 1288187 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.9441. Min Act: -0.0000

Data Index: 223496 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.9045. Min Act: -0.0000

Data Index: 124386 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8664. Min Act: -0.0000

Data Index: 486 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8114. Min Act: -0.0000

Data Index: 390692 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.7622. Min Act: -0.0000

Data Index: 996913 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.7739. Min Act: -0.0000

Data Index: 456151 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.7172. Min Act: -0.0000

Data Index: 789221 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.8815. Min Act: -0.0000

Data Index: 997188 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.6318. Min Act: -0.0000

Data Index: 814022 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.6229. Min Act: -0.0000

Data Index: 935162 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.7653. Min Act: -0.0000

Data Index: 30899 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.7045. Min Act: -0.0000

Data Index: 1222625 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.6679. Min Act: -0.0000

Data Index: 916984 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.6132. Min Act: -0.0000

Data Index: 733803 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.5531. Min Act: -0.0000

Data Index: 1130625 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.6373. Min Act: -0.0000

Data Index: 1059499 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.5260. Min Act: -0.0000

Data Index: 184561 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 2.1880. Min Range: -2.1880

Max Act: 1.5836. Min Act: -0.0000

Data Index: 912413 (C4 (Web Text))

Max Activating Token Index: 170