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

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

Neuron 4999 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: 1.7265. Min Range: -1.7265

Max Act: 1.6042. Min Act: -0.0000

Data Index: 1229879 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.7265. Min Act: -0.0000

Data Index: 1252364 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.4918. Min Act: -0.0000

Data Index: 378829 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.4700. Min Act: -0.0000

Data Index: 118834 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1217259 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.3804. Min Act: 0.0000

Data Index: 472123 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2572. Min Act: -0.0000

Data Index: 62656 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2125. Min Act: -0.0000

Data Index: 1156443 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.1215. Min Act: -0.0000

Data Index: 165591 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2674. Min Act: -0.0000

Data Index: 58390 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2202. Min Act: -0.0000

Data Index: 366871 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1215776 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2930. Min Act: -0.0000

Data Index: 1019398 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1059465 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.1434. Min Act: -0.0000

Data Index: 280057 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2118. Min Act: -0.0000

Data Index: 689107 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.2793. Min Act: -0.0000

Data Index: 816365 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1202998 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.1841. Min Act: -0.0000

Data Index: 106904 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.7265. Min Range: -1.7265

Max Act: 1.1678. Min Act: -0.0000

Data Index: 842836 (C4 (Web Text))

Max Activating Token Index: 687