Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5837 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1219067 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0001

Data Index: 206371 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1080116 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0785. Min Act: -0.0001

Data Index: 849144 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0743. Min Act: -0.0001

Data Index: 284269 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0767. Min Act: -0.0001

Data Index: 169076 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0796. Min Act: -0.0001

Data Index: 781491 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1113386 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0767. Min Act: -0.0001

Data Index: 557745 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1192708 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0676. Min Act: -0.0001

Data Index: 259189 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0717. Min Act: -0.0001

Data Index: 430304 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0664. Min Act: -0.0001

Data Index: 385790 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0666. Min Act: -0.0001

Data Index: 398409 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0600. Min Act: -0.0001

Data Index: 590689 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1205144 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0518. Min Act: -0.0001

Data Index: 555362 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0386. Min Act: -0.0001

Data Index: 421859 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0440. Min Act: -0.0001

Data Index: 309111 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0449. Min Act: -0.0002

Data Index: 873395 (C4 (Web Text))

Max Activating Token Index: 991