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

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

Neuron 3036 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.0602. Min Act: -0.0001

Data Index: 685422 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.3707. Min Act: -0.0001

Data Index: 496870 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.5691. Min Act: -0.0001

Data Index: 294959 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.2853. Min Act: -0.0002

Data Index: 1088299 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 4.5021. Min Range: -4.5021

Max Act: 4.5021. Min Act: -0.0002

Data Index: 299406 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.5679. Min Act: -0.0001

Data Index: 525022 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.5715. Min Act: -0.0002

Data Index: 315849 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.7077. Min Act: -0.0001

Data Index: 469958 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.2264. Min Act: -0.0001

Data Index: 408987 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.6331. Min Act: -0.0001

Data Index: 383497 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.7438. Min Act: -0.0001

Data Index: 471225 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.3410. Min Act: -0.0001

Data Index: 165898 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.4494. Min Act: -0.0002

Data Index: 605230 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.9006. Min Act: -0.0001

Data Index: 1260024 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.8952. Min Act: -0.0002

Data Index: 6227 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.4274. Min Act: -0.0002

Data Index: 68979 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.3869. Min Act: -0.0001

Data Index: 619500 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.4862. Min Act: -0.0001

Data Index: 380991 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 4.5021. Min Range: -4.5021

Max Act: 3.2966. Min Act: -0.0002

Data Index: 428990 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 4.5021. Min Range: -4.5021

Max Act: 2.8546. Min Act: -0.0001

Data Index: 1125140 (C4 (Web Text))

Max Activating Token Index: 674