Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2607 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.7245. Min Act: -0.0001

Data Index: 592539 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6501. Min Act: -0.0001

Data Index: 905612 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6687. Min Act: -0.0001

Data Index: 744844 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6930. Min Act: -0.0001

Data Index: 227885 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6558. Min Act: -0.0001

Data Index: 815436 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6184. Min Act: -0.0001

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6292. Min Act: -0.0001

Data Index: 321021 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6226. Min Act: -0.0001

Data Index: 40746 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5422. Min Act: -0.0001

Data Index: 686036 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6086. Min Act: -0.0001

Data Index: 79189 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5839. Min Act: -0.0001

Data Index: 292895 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6068. Min Act: -0.0001

Data Index: 887309 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6051. Min Act: -0.0001

Data Index: 533979 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5724. Min Act: -0.0001

Data Index: 160605 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5835. Min Act: -0.0001

Data Index: 1172178 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5804. Min Act: -0.0001

Data Index: 1144978 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6146. Min Act: -0.0001

Data Index: 665357 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5734. Min Act: -0.0001

Data Index: 493613 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5771. Min Act: -0.0001

Data Index: 141644 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5805. Min Act: -0.0001

Data Index: 846853 (C4 (Web Text))

Max Activating Token Index: 986