Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2996 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0899. Min Act: -0.0003

Data Index: 707856 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.1090. Min Act: -0.0003

Data Index: 202564 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0963. Min Act: -0.0003

Data Index: 703029 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0863. Min Act: -0.0003

Data Index: 1258169 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0868. Min Act: -0.0003

Data Index: 1019709 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0772. Min Act: -0.0003

Data Index: 840791 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0831. Min Act: -0.0003

Data Index: 909352 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0892. Min Act: -0.0003

Data Index: 580329 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0899. Min Act: -0.0003

Data Index: 841816 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0833. Min Act: -0.0003

Data Index: 402458 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0748. Min Act: -0.0003

Data Index: 637684 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0808. Min Act: -0.0003

Data Index: 127018 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0798. Min Act: -0.0003

Data Index: 454375 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0795. Min Act: -0.0003

Data Index: 961393 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0824. Min Act: -0.0003

Data Index: 702068 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0793. Min Act: -0.0003

Data Index: 743938 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0815. Min Act: -0.0003

Data Index: 1062044 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0843. Min Act: -0.0003

Data Index: 731385 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1116568 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.1090. Min Range: -0.1090

Max Act: 0.0811. Min Act: -0.0003

Data Index: 1059501 (C4 (Web Text))

Max Activating Token Index: 483