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

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

Neuron 397 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: 0.1049. Min Range: -0.1049

Max Act: 0.1025. Min Act: -0.0002

Data Index: 582508 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1211474 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0948. Min Act: -0.0002

Data Index: 55419 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1093229 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0957. Min Act: -0.0002

Data Index: 41035 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0879. Min Act: -0.0002

Data Index: 390615 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0817. Min Act: -0.0002

Data Index: 381078 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0805. Min Act: -0.0002

Data Index: 377355 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1020184 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0798. Min Act: -0.0002

Data Index: 686469 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0781. Min Act: -0.0002

Data Index: 579627 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0787. Min Act: -0.0002

Data Index: 413410 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0778. Min Act: -0.0002

Data Index: 900729 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0754. Min Act: -0.0002

Data Index: 913843 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0691. Min Act: -0.0002

Data Index: 927464 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0657. Min Act: -0.0002

Data Index: 330283 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0695. Min Act: -0.0002

Data Index: 672630 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0681. Min Act: -0.0002

Data Index: 850314 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0655. Min Act: -0.0002

Data Index: 146890 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0636. Min Act: -0.0002

Data Index: 538089 (C4 (Web Text))

Max Activating Token Index: 846