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

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

Neuron 2877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6556. Min Act: -0.0000

Data Index: 411982 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5232. Min Act: -0.0000

Data Index: 631257 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4833. Min Act: -0.0000

Data Index: 920726 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1626202 (Python Code)

Max Activating Token Index: 960

Text #4

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1621281 (Python Code)

Max Activating Token Index: 984

Text #5

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4242. Min Act: 0.0000

Data Index: 544222 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1546353 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1268694 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1630809 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1617761 (Python Code)

Max Activating Token Index: 78

Text #10

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1494283 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1033531 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1420659 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1229278 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1245018 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1552031 (Python Code)

Max Activating Token Index: 829

Text #16

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.3638. Min Act: -0.0000

Data Index: 484885 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.3641. Min Act: -0.0000

Data Index: 31010 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.3349. Min Act: -0.0000

Data Index: 320012 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1306201 (C4 (Web Text))

Max Activating Token Index: 781