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

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

Neuron 3813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0001

Data Index: 360458 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1222482 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1016. Min Act: -0.0001

Data Index: 523925 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1274696 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0965. Min Act: -0.0001

Data Index: 498502 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0788. Min Act: -0.0001

Data Index: 542575 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1061439 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1009079 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0876. Min Act: -0.0001

Data Index: 287809 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0879. Min Act: -0.0001

Data Index: 828154 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0938. Min Act: -0.0001

Data Index: 482437 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0908. Min Act: -0.0001

Data Index: 651916 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1274994 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0799. Min Act: -0.0001

Data Index: 175089 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0813. Min Act: -0.0001

Data Index: 225186 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1032543 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0793. Min Act: -0.0001

Data Index: 431052 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0820. Min Act: -0.0001

Data Index: 526370 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0796. Min Act: -0.0001

Data Index: 277383 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1070483 (C4 (Web Text))

Max Activating Token Index: 166