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

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

Neuron 3985 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0022. Min Act: -0.0002

Data Index: 1449647 (Python Code)

Max Activating Token Index: 452

Text #1

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0016. Min Act: -0.0002

Data Index: 1526795 (Python Code)

Max Activating Token Index: 792

Text #2

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0014. Min Act: -0.0002

Data Index: 1056837 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0013. Min Act: -0.0003

Data Index: 977817 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0012. Min Act: -0.0003

Data Index: 1137679 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1508931 (Python Code)

Max Activating Token Index: 806

Text #6

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0012. Min Act: -0.0003

Data Index: 583072 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1173785 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0012. Min Act: -0.0003

Data Index: 906465 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1654316 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0012. Min Act: -0.0003

Data Index: 615712 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0012. Min Act: -0.0003

Data Index: 46389 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1307395 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0003

Data Index: 517243 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0003

Data Index: 537303 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0003

Data Index: 760519 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1478519 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0003

Data Index: 268592 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0002

Data Index: 540840 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.0022. Min Range: -0.0022

Max Act: 0.0011. Min Act: -0.0003

Data Index: 654241 (C4 (Web Text))

Max Activating Token Index: 233