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

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

Neuron 4963 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: 0.1289. Min Range: -0.1289

Max Act: 0.1289. Min Act: -0.0001

Data Index: 537431 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1081. Min Act: -0.0001

Data Index: 102802 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1167. Min Act: -0.0001

Data Index: 5332 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1221. Min Act: -0.0001

Data Index: 569267 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1122315 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0949. Min Act: -0.0001

Data Index: 165300 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0990. Min Act: -0.0001

Data Index: 539733 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0954. Min Act: -0.0001

Data Index: 210570 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1004. Min Act: -0.0001

Data Index: 654218 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1014. Min Act: -0.0001

Data Index: 1024141 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1031383 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0802. Min Act: -0.0001

Data Index: 20024 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0984. Min Act: -0.0001

Data Index: 500441 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1045. Min Act: -0.0001

Data Index: 14841 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1279426 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1108140 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0941. Min Act: -0.0001

Data Index: 289406 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0898. Min Act: -0.0001

Data Index: 250668 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1118720 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.1289. Min Range: -0.1289

Max Act: 0.1037. Min Act: -0.0001

Data Index: 713276 (C4 (Web Text))

Max Activating Token Index: 77