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

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

Neuron 749 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: 1.9668. Min Range: -1.9668

Max Act: 1.9668. Min Act: -0.0002

Data Index: 1125655 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.7685. Min Act: -0.0002

Data Index: 65079 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.6734. Min Act: -0.0001

Data Index: 395887 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5659. Min Act: -0.0002

Data Index: 174209 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4940. Min Act: -0.0002

Data Index: 830391 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4971. Min Act: -0.0001

Data Index: 1009469 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5719. Min Act: -0.0001

Data Index: 1300533 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5880. Min Act: -0.0002

Data Index: 146000 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.7058. Min Act: -0.0001

Data Index: 715742 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3668. Min Act: -0.0001

Data Index: 349036 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4546. Min Act: -0.0001

Data Index: 591092 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4353. Min Act: -0.0002

Data Index: 955645 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5098. Min Act: -0.0001

Data Index: 748391 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4934. Min Act: -0.0002

Data Index: 755937 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4685. Min Act: -0.0002

Data Index: 1018846 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3891. Min Act: -0.0002

Data Index: 258891 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.4715. Min Act: -0.0002

Data Index: 183103 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3460. Min Act: -0.0001

Data Index: 593967 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.3448. Min Act: -0.0002

Data Index: 138440 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.9668. Min Range: -1.9668

Max Act: 1.5021. Min Act: -0.0002

Data Index: 885958 (C4 (Web Text))

Max Activating Token Index: 864