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

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

Neuron 3992 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: 0.0095. Min Range: -0.0095

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1165446 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0093. Min Act: -0.0002

Data Index: 904776 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0089. Min Act: -0.0003

Data Index: 986511 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0088. Min Act: -0.0003

Data Index: 693067 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1070143 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1388113 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1521378 (Python Code)

Max Activating Token Index: 436

Text #7

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1543185 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1528801 (Python Code)

Max Activating Token Index: 609

Text #9

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1530930 (Python Code)

Max Activating Token Index: 560

Text #10

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0078. Min Act: -0.0003

Data Index: 934120 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1302082 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1170330 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1603912 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1606004 (Python Code)

Max Activating Token Index: 581

Text #15

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0075. Min Act: -0.0003

Data Index: 463379 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0073. Min Act: -0.0003

Data Index: 1054890 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1478600 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0069. Min Act: -0.0003

Data Index: 979356 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.0095. Min Range: -0.0095

Max Act: 0.0076. Min Act: -0.0003

Data Index: 963106 (C4 (Web Text))

Max Activating Token Index: 332