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

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

Neuron 2010 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0003

Data Index: 94567 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0960. Min Act: -0.0004

Data Index: 189114 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0988. Min Act: -0.0003

Data Index: 938551 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0978. Min Act: -0.0003

Data Index: 1125003 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0962. Min Act: -0.0003

Data Index: 775611 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0948. Min Act: -0.0003

Data Index: 611535 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0901. Min Act: -0.0003

Data Index: 670641 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0928. Min Act: -0.0004

Data Index: 1138561 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0924. Min Act: -0.0004

Data Index: 1021277 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0944. Min Act: -0.0003

Data Index: 1252477 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0907. Min Act: -0.0004

Data Index: 509570 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0906. Min Act: -0.0003

Data Index: 1103420 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0903. Min Act: -0.0003

Data Index: 117242 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0901. Min Act: -0.0004

Data Index: 890688 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0863. Min Act: -0.0003

Data Index: 1018554 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0889. Min Act: -0.0004

Data Index: 411571 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0890. Min Act: -0.0003

Data Index: 280979 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1248536 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0890. Min Act: -0.0003

Data Index: 790405 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0851. Min Act: -0.0003

Data Index: 74231 (C4 (Web Text))

Max Activating Token Index: 632