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

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

Neuron 5002 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1232. Min Act: -0.0003

Data Index: 1138148 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1151. Min Act: -0.0002

Data Index: 1315836 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1021. Min Act: -0.0003

Data Index: 55889 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1034. Min Act: -0.0003

Data Index: 1278738 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1071. Min Act: -0.0003

Data Index: 1222070 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1029. Min Act: -0.0003

Data Index: 480491 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1035. Min Act: -0.0003

Data Index: 1555717 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1406386 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1020. Min Act: -0.0003

Data Index: 991275 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1059. Min Act: -0.0003

Data Index: 958142 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1014. Min Act: -0.0003

Data Index: 1536759 (Python Code)

Max Activating Token Index: 709

Text #11

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1015. Min Act: -0.0003

Data Index: 884658 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0971. Min Act: -0.0003

Data Index: 1577382 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.1031. Min Act: -0.0003

Data Index: 362780 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1073866 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0997. Min Act: -0.0003

Data Index: 80472 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0988. Min Act: -0.0003

Data Index: 1248327 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1540913 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1564924 (Python Code)

Max Activating Token Index: 266

Text #19

Max Range: 0.1232. Min Range: -0.1232

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1364823 (Python Code)

Max Activating Token Index: 446