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

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

Neuron 1131 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: 0.8914. Min Range: -0.8914

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1346421 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.8240. Min Act: -0.0000

Data Index: 914414 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1222894 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1035685 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7791. Min Act: -0.0000

Data Index: 106819 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.8026. Min Act: -0.0000

Data Index: 339091 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7915. Min Act: -0.0000

Data Index: 383978 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7539. Min Act: -0.0000

Data Index: 283146 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1261646 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7464. Min Act: -0.0000

Data Index: 666173 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.7236. Min Act: -0.0000

Data Index: 742507 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6830. Min Act: -0.0000

Data Index: 731889 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6856. Min Act: -0.0000

Data Index: 559775 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6744. Min Act: -0.0000

Data Index: 846828 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6676. Min Act: -0.0000

Data Index: 492185 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6535. Min Act: -0.0000

Data Index: 64896 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6789. Min Act: -0.0000

Data Index: 319012 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6370. Min Act: -0.0000

Data Index: 634832 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6516. Min Act: -0.0000

Data Index: 608085 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.8914. Min Range: -0.8914

Max Act: 0.6929. Min Act: -0.0000

Data Index: 62185 (C4 (Web Text))

Max Activating Token Index: 330