Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 350 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9672. Min Act: -0.0000

Data Index: 222996 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.0533. Min Range: -1.0533

Max Act: 1.0533. Min Act: -0.0000

Data Index: 111580 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1341855 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1262353 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9680. Min Act: -0.0000

Data Index: 122076 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1308760 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9449. Min Act: -0.0000

Data Index: 476490 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8637. Min Act: -0.0000

Data Index: 978474 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8524. Min Act: -0.0000

Data Index: 761319 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1137028 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8601. Min Act: -0.0000

Data Index: 265459 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9274. Min Act: -0.0000

Data Index: 961286 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8352. Min Act: -0.0000

Data Index: 795600 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9053. Min Act: -0.0000

Data Index: 109119 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1013756 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8508. Min Act: -0.0000

Data Index: 551067 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8850. Min Act: -0.0000

Data Index: 670494 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9666. Min Act: -0.0000

Data Index: 390818 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.8700. Min Act: -0.0000

Data Index: 824552 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.0533. Min Range: -1.0533

Max Act: 0.9294. Min Act: -0.0000

Data Index: 667244 (C4 (Web Text))

Max Activating Token Index: 830