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

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

Neuron 447 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2062. Min Act: -0.0001

Data Index: 596249 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2070. Min Act: -0.0001

Data Index: 857347 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2265. Min Act: -0.0001

Data Index: 460792 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1003500 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2012. Min Act: -0.0001

Data Index: 566923 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1925. Min Act: -0.0001

Data Index: 704587 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.2002. Min Act: -0.0001

Data Index: 367093 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1992. Min Act: -0.0001

Data Index: 633657 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1171665 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1953. Min Act: -0.0001

Data Index: 221106 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1865. Min Act: -0.0001

Data Index: 849210 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1071456 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1935. Min Act: -0.0001

Data Index: 641424 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1870. Min Act: -0.0001

Data Index: 228510 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1869. Min Act: -0.0001

Data Index: 1167324 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1892. Min Act: -0.0001

Data Index: 444380 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1076536 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1807. Min Act: -0.0001

Data Index: 518904 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1867. Min Act: -0.0001

Data Index: 568234 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.2265. Min Range: -0.2265

Max Act: 0.1867. Min Act: -0.0001

Data Index: 51816 (C4 (Web Text))

Max Activating Token Index: 113