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

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

Neuron 2753 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: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0001

Data Index: 477542 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0922. Min Act: -0.0001

Data Index: 598358 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0877. Min Act: -0.0001

Data Index: 31036 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0898. Min Act: -0.0000

Data Index: 316 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1539062 (Python Code)

Max Activating Token Index: 227

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1057346 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0838. Min Act: -0.0001

Data Index: 50511 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0853. Min Act: -0.0000

Data Index: 552697 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1099199 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0813. Min Act: -0.0000

Data Index: 783390 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0776. Min Act: -0.0000

Data Index: 432008 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0794. Min Act: -0.0000

Data Index: 474859 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0824. Min Act: -0.0000

Data Index: 712345 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1038996 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0782. Min Act: -0.0001

Data Index: 65121 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0754. Min Act: -0.0000

Data Index: 18689 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0750. Min Act: -0.0000

Data Index: 190812 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0765. Min Act: -0.0000

Data Index: 757947 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1248786 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1106454 (C4 (Web Text))

Max Activating Token Index: 176