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

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

Neuron 3975 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0002

Data Index: 903882 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1255864 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1067. Min Act: -0.0002

Data Index: 796224 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1032374 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1045. Min Act: -0.0002

Data Index: 794979 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1065. Min Act: -0.0002

Data Index: 806247 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1050. Min Act: -0.0002

Data Index: 816317 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1286216 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1180236 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1144663 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1006. Min Act: -0.0002

Data Index: 322453 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1003. Min Act: -0.0002

Data Index: 902353 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1014. Min Act: -0.0002

Data Index: 634648 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0947. Min Act: -0.0002

Data Index: 310693 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1129552 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1107475 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1016502 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0919. Min Act: -0.0002

Data Index: 854408 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0919. Min Act: -0.0002

Data Index: 229709 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0909. Min Act: -0.0002

Data Index: 949598 (C4 (Web Text))

Max Activating Token Index: 113