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

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

Neuron 1950 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1056279 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0001

Data Index: 300312 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0813. Min Act: -0.0001

Data Index: 334621 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0831. Min Act: -0.0001

Data Index: 963647 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0758. Min Act: -0.0001

Data Index: 977492 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0785. Min Act: -0.0001

Data Index: 707149 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0667. Min Act: -0.0001

Data Index: 630457 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0760. Min Act: -0.0001

Data Index: 150486 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1338357 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0688. Min Act: -0.0001

Data Index: 554553 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0720. Min Act: -0.0001

Data Index: 973802 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0714. Min Act: -0.0001

Data Index: 970581 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1084549 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0723. Min Act: -0.0001

Data Index: 449887 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0728. Min Act: -0.0001

Data Index: 875064 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0633. Min Act: -0.0001

Data Index: 142803 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0681. Min Act: -0.0001

Data Index: 842261 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1088033 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1254155 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0652. Min Act: -0.0001

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 206