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

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

Neuron 2165 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1251274 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1120097 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1228. Min Act: -0.0001

Data Index: 158058 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1109. Min Act: -0.0001

Data Index: 657464 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1005. Min Act: -0.0001

Data Index: 716323 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0999. Min Act: -0.0001

Data Index: 38383 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1014. Min Act: -0.0001

Data Index: 239134 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1062. Min Act: -0.0001

Data Index: 352646 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1121684 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.1086. Min Act: -0.0001

Data Index: 877713 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0947. Min Act: -0.0001

Data Index: 743848 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0797. Min Act: -0.0001

Data Index: 1082537 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0935. Min Act: -0.0001

Data Index: 857546 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0966. Min Act: -0.0001

Data Index: 358817 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0898. Min Act: -0.0001

Data Index: 485951 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0961. Min Act: -0.0001

Data Index: 788801 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0921. Min Act: -0.0001

Data Index: 751806 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0856. Min Act: -0.0001

Data Index: 273392 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0878. Min Act: -0.0001

Data Index: 601604 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.1228. Min Range: -0.1228

Max Act: 0.0856. Min Act: -0.0001

Data Index: 909675 (C4 (Web Text))

Max Activating Token Index: 637