Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 219 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0777. Min Act: -0.0002

Data Index: 874595 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0002

Data Index: 625846 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1473753 (Python Code)

Max Activating Token Index: 336

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1389046 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0699. Min Act: -0.0002

Data Index: 709158 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1331716 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1008291 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0736. Min Act: -0.0002

Data Index: 992068 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0759. Min Act: -0.0002

Data Index: 565259 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0733. Min Act: -0.0002

Data Index: 173010 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0743. Min Act: -0.0002

Data Index: 335041 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0713. Min Act: -0.0002

Data Index: 325449 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0736. Min Act: -0.0002

Data Index: 30112 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1347937 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1010318 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0712. Min Act: -0.0002

Data Index: 185636 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1004503 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1018726 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0723. Min Act: -0.0002

Data Index: 220510 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0682. Min Act: -0.0002

Data Index: 410625 (C4 (Web Text))

Max Activating Token Index: 278