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

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

Neuron 3661 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0807. Min Act: -0.0002

Data Index: 749434 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0672. Min Act: -0.0003

Data Index: 18219 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.0807. Min Range: -1.0807

Max Act: 1.0368. Min Act: -0.0002

Data Index: 410100 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9872. Min Act: -0.0003

Data Index: 427978 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9950. Min Act: -0.0002

Data Index: 251368 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9830. Min Act: -0.0002

Data Index: 1069474 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9688. Min Act: -0.0002

Data Index: 548775 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9710. Min Act: -0.0002

Data Index: 383662 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9826. Min Act: -0.0002

Data Index: 526643 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9704. Min Act: -0.0002

Data Index: 530850 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9569. Min Act: -0.0002

Data Index: 1006846 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9802. Min Act: -0.0002

Data Index: 352547 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9870. Min Act: -0.0003

Data Index: 302153 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9569. Min Act: -0.0002

Data Index: 106239 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9766. Min Act: -0.0002

Data Index: 788764 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9655. Min Act: -0.0002

Data Index: 558147 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9556. Min Act: -0.0002

Data Index: 591848 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9553. Min Act: -0.0002

Data Index: 805744 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9633. Min Act: -0.0003

Data Index: 917906 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 1.0807. Min Range: -1.0807

Max Act: 0.9557. Min Act: -0.0003

Data Index: 749987 (C4 (Web Text))

Max Activating Token Index: 544