Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3586 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2531. Min Act: -0.0001

Data Index: 46340 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2377. Min Act: -0.0002

Data Index: 730721 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2056. Min Act: -0.0002

Data Index: 464091 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1964. Min Act: -0.0002

Data Index: 393471 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1951. Min Act: -0.0002

Data Index: 407415 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1988. Min Act: -0.0002

Data Index: 31913 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1825. Min Act: -0.0002

Data Index: 539866 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2115. Min Act: -0.0002

Data Index: 367118 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2043. Min Act: -0.0002

Data Index: 577437 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1882. Min Act: -0.0001

Data Index: 299375 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1898. Min Act: -0.0002

Data Index: 443324 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1934. Min Act: -0.0001

Data Index: 430209 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1875. Min Act: -0.0001

Data Index: 281749 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1789. Min Act: -0.0002

Data Index: 1320423 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1734. Min Act: -0.0001

Data Index: 67591 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1779. Min Act: -0.0001

Data Index: 520496 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1794. Min Act: -0.0001

Data Index: 648499 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1903. Min Act: -0.0001

Data Index: 771851 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1851. Min Act: -0.0001

Data Index: 288824 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1675. Min Act: -0.0002

Data Index: 590710 (C4 (Web Text))

Max Activating Token Index: 794