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

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

Neuron 4524 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: 0.1421. Min Range: -0.1421

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1208740 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1149458 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1146. Min Act: -0.0000

Data Index: 972848 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1184. Min Act: -0.0000

Data Index: 598323 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0953. Min Act: -0.0000

Data Index: 416861 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1124657 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1185522 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1022. Min Act: -0.0000

Data Index: 612977 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1007887 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1507242 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0901. Min Act: -0.0000

Data Index: 598438 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1303516 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1585345 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0840. Min Act: -0.0000

Data Index: 293879 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0897. Min Act: -0.0000

Data Index: 937076 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0777. Min Act: -0.0000

Data Index: 191735 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0811. Min Act: -0.0000

Data Index: 225261 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1332600 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0832. Min Act: -0.0000

Data Index: 830928 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1294869 (C4 (Web Text))

Max Activating Token Index: 1007