Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1678 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.1834. Min Act: -0.0000

Data Index: 576848 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.0252. Min Act: -0.0000

Data Index: 233425 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.0918. Min Act: -0.0000

Data Index: 760987 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1220853 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.1834. Min Range: -1.1834

Max Act: 1.0644. Min Act: -0.0000

Data Index: 464844 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1284936 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.9024. Min Act: -0.0000

Data Index: 36894 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1254844 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.8602. Min Act: -0.0000

Data Index: 519384 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.8446. Min Act: -0.0000

Data Index: 864649 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.7861. Min Act: -0.0000

Data Index: 739990 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.8223. Min Act: -0.0000

Data Index: 602516 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1233274 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.7886. Min Act: -0.0000

Data Index: 2744 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.8315. Min Act: -0.0000

Data Index: 744552 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1314425 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.7508. Min Act: -0.0000

Data Index: 20024 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.7185. Min Act: -0.0000

Data Index: 712348 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1261362 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.1834. Min Range: -1.1834

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1070793 (C4 (Web Text))

Max Activating Token Index: 927