Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 529 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0005

Data Index: 1542738 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0782. Min Act: -0.0005

Data Index: 331762 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0761. Min Act: -0.0005

Data Index: 732431 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0720. Min Act: -0.0005

Data Index: 1338354 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0740. Min Act: -0.0005

Data Index: 1242989 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0803. Min Act: -0.0005

Data Index: 133011 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0764. Min Act: -0.0005

Data Index: 869807 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0739. Min Act: -0.0005

Data Index: 749388 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0722. Min Act: -0.0005

Data Index: 1450715 (Python Code)

Max Activating Token Index: 563

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0684. Min Act: -0.0005

Data Index: 698496 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0734. Min Act: -0.0005

Data Index: 819333 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0655. Min Act: -0.0005

Data Index: 858028 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0700. Min Act: -0.0005

Data Index: 977034 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0684. Min Act: -0.0005

Data Index: 1448689 (Python Code)

Max Activating Token Index: 779

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0695. Min Act: -0.0005

Data Index: 792924 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0700. Min Act: -0.0005

Data Index: 1377331 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0695. Min Act: -0.0005

Data Index: 1509496 (Python Code)

Max Activating Token Index: 1009

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0625. Min Act: -0.0005

Data Index: 39553 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0641. Min Act: -0.0005

Data Index: 1648866 (Python Code)

Max Activating Token Index: 608

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0558. Min Act: -0.0005

Data Index: 803400 (C4 (Web Text))

Max Activating Token Index: 1023