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

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

Neuron 2308 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1391542 (Python Code)

Max Activating Token Index: 551

Text #1

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1297602 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1308995 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1009576 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1055741 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1369928 (Python Code)

Max Activating Token Index: 796

Text #6

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2068. Min Act: -0.0000

Data Index: 727739 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1493138 (Python Code)

Max Activating Token Index: 599

Text #8

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1940. Min Act: -0.0000

Data Index: 892129 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2028. Min Act: -0.0000

Data Index: 851866 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1842. Min Act: 0.0000

Data Index: 1378223 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1877. Min Act: -0.0000

Data Index: 708657 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1668. Min Act: -0.0000

Data Index: 1476859 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1928. Min Act: -0.0000

Data Index: 924708 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1844. Min Act: -0.0000

Data Index: 597473 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1264524 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1959. Min Act: -0.0000

Data Index: 618766 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1690. Min Act: -0.0000

Data Index: 112951 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1161081 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1892. Min Act: -0.0000

Data Index: 892983 (C4 (Web Text))

Max Activating Token Index: 290