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

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

Neuron 1970 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1149652 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1275026 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1227. Min Act: -0.0000

Data Index: 967761 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1169. Min Act: -0.0000

Data Index: 649121 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1070396 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1344933 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1118. Min Act: -0.0000

Data Index: 616800 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1085. Min Act: -0.0000

Data Index: 792661 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1151. Min Act: -0.0000

Data Index: 171199 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1071. Min Act: -0.0000

Data Index: 156950 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1024. Min Act: -0.0000

Data Index: 647206 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1056. Min Act: -0.0000

Data Index: 370598 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1042. Min Act: -0.0000

Data Index: 419533 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1012. Min Act: -0.0000

Data Index: 332937 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1059. Min Act: -0.0000

Data Index: 294868 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0876. Min Act: -0.0000

Data Index: 157421 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1023842 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.0910. Min Act: -0.0000

Data Index: 885244 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1267495 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.1502. Min Range: -0.1502

Max Act: 0.1022. Min Act: -0.0000

Data Index: 823450 (C4 (Web Text))

Max Activating Token Index: 342