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

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

Neuron 4014 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.4730. Min Act: -0.0000

Data Index: 557666 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3917. Min Act: -0.0000

Data Index: 790003 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2939. Min Act: -0.0000

Data Index: 2271 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2852. Min Act: -0.0000

Data Index: 544698 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1380. Min Act: -0.0000

Data Index: 567923 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1205. Min Act: -0.0000

Data Index: 735554 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0288. Min Act: -0.0000

Data Index: 996404 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0586. Min Act: -0.0000

Data Index: 785714 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0788. Min Act: -0.0000

Data Index: 900278 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0757. Min Act: -0.0000

Data Index: 338370 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0091. Min Act: -0.0000

Data Index: 471387 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1181751 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0628. Min Act: -0.0000

Data Index: 561652 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0621. Min Act: -0.0000

Data Index: 1200765 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1287713 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1229930 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0979. Min Act: -0.0000

Data Index: 838924 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1070184 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0802. Min Act: -0.0000

Data Index: 172799 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0370. Min Act: -0.0000

Data Index: 606641 (C4 (Web Text))

Max Activating Token Index: 465