Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3310 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0002

Data Index: 481541 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1238262 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0903. Min Act: -0.0002

Data Index: 581024 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1212932 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1115668 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0877. Min Act: -0.0002

Data Index: 214617 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0901. Min Act: -0.0002

Data Index: 449395 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1180607 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0817. Min Act: -0.0002

Data Index: 470982 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1350650 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0787. Min Act: -0.0002

Data Index: 160989 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0819. Min Act: -0.0002

Data Index: 169935 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0809. Min Act: -0.0002

Data Index: 875906 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0804. Min Act: -0.0002

Data Index: 82896 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0831. Min Act: -0.0002

Data Index: 309456 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0821. Min Act: -0.0002

Data Index: 497132 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0819. Min Act: -0.0002

Data Index: 406659 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0769. Min Act: -0.0002

Data Index: 877770 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0796. Min Act: -0.0002

Data Index: 548484 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0784. Min Act: -0.0002

Data Index: 848201 (C4 (Web Text))

Max Activating Token Index: 287