Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4571 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0993. Min Act: -0.0002

Data Index: 490134 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0935. Min Act: -0.0002

Data Index: 844585 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1096948 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0992. Min Act: -0.0002

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0925. Min Act: -0.0002

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0919. Min Act: -0.0002

Data Index: 512623 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1263906 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0854. Min Act: -0.0002

Data Index: 177229 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0895. Min Act: -0.0002

Data Index: 377773 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0940. Min Act: -0.0002

Data Index: 827686 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0843. Min Act: -0.0002

Data Index: 147521 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1021496 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1368943 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0782. Min Act: -0.0002

Data Index: 489349 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0721. Min Act: -0.0002

Data Index: 115535 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1355055 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0720. Min Act: -0.0002

Data Index: 722025 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0747. Min Act: -0.0002

Data Index: 291313 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0783. Min Act: -0.0002

Data Index: 991755 (C4 (Web Text))

Max Activating Token Index: 790