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

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

Neuron 1338 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1531775 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0913. Min Act: 0.0001

Data Index: 1480861 (Python Code)

Max Activating Token Index: 776

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0945. Min Act: -0.0000

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0924. Min Act: -0.0000

Data Index: 186166 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1329999 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0840. Min Act: -0.0000

Data Index: 811809 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0765. Min Act: 0.0000

Data Index: 1370811 (Python Code)

Max Activating Token Index: 249

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1460167 (Python Code)

Max Activating Token Index: 531

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0766. Min Act: -0.0000

Data Index: 369847 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0698. Min Act: -0.0000

Data Index: 457083 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1002184 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1600716 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0676. Min Act: -0.0000

Data Index: 600709 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0705. Min Act: 0.0001

Data Index: 1432379 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0723. Min Act: -0.0000

Data Index: 303004 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1380059 (Python Code)

Max Activating Token Index: 749

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1050333 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0744. Min Act: -0.0000

Data Index: 290627 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1602119 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0736. Min Act: -0.0000

Data Index: 121123 (C4 (Web Text))

Max Activating Token Index: 939