Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1106. Min Act: -0.0004

Data Index: 76484 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1057. Min Act: -0.0004

Data Index: 647319 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1088. Min Act: -0.0004

Data Index: 350875 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0993. Min Act: -0.0004

Data Index: 242339 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1066. Min Act: -0.0004

Data Index: 1033151 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0004

Data Index: 746222 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1025. Min Act: -0.0004

Data Index: 245961 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1013. Min Act: -0.0004

Data Index: 237205 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1057. Min Act: -0.0004

Data Index: 642281 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0981. Min Act: -0.0004

Data Index: 945144 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0971. Min Act: -0.0004

Data Index: 1277806 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1000. Min Act: -0.0004

Data Index: 729594 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1036. Min Act: -0.0004

Data Index: 84770 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1071. Min Act: -0.0004

Data Index: 1164913 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0991. Min Act: -0.0004

Data Index: 1019955 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1011. Min Act: -0.0004

Data Index: 1011338 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0978. Min Act: -0.0004

Data Index: 427350 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0903. Min Act: -0.0004

Data Index: 199239 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0969. Min Act: -0.0004

Data Index: 365393 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0917. Min Act: -0.0004

Data Index: 372032 (C4 (Web Text))

Max Activating Token Index: 404