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

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

Neuron 515 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1921. Min Act: -0.0002

Data Index: 887204 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1816. Min Act: -0.0002

Data Index: 107304 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1813. Min Act: -0.0002

Data Index: 1079677 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1829. Min Act: -0.0002

Data Index: 536562 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1635. Min Act: -0.0002

Data Index: 979984 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1743. Min Act: -0.0002

Data Index: 37727 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1603. Min Act: -0.0002

Data Index: 1124279 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1833. Min Act: -0.0002

Data Index: 1192925 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1828. Min Act: -0.0002

Data Index: 670065 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1476. Min Act: -0.0002

Data Index: 243277 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1673. Min Act: -0.0002

Data Index: 750494 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1156. Min Act: -0.0002

Data Index: 1123203 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1630. Min Act: -0.0002

Data Index: 987682 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1635. Min Act: -0.0002

Data Index: 1344404 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1524. Min Act: -0.0002

Data Index: 1036010 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1309. Min Act: -0.0002

Data Index: 813238 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1482. Min Act: -0.0002

Data Index: 1013364 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1651. Min Act: -0.0002

Data Index: 610854 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1463. Min Act: -0.0002

Data Index: 78910 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1224063 (C4 (Web Text))

Max Activating Token Index: 598