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

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

Neuron 4803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2822. Min Range: -2.2822

Max Act: 2.2822. Min Act: -0.0000

Data Index: 1199196 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.9558. Min Act: -0.0000

Data Index: 871202 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 2.2822. Min Range: -2.2822

Max Act: 2.0336. Min Act: -0.0000

Data Index: 775897 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.8876. Min Act: -0.0000

Data Index: 533579 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.8619. Min Act: -0.0000

Data Index: 518727 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.7892. Min Act: -0.0000

Data Index: 324265 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.6309. Min Act: -0.0000

Data Index: 276228 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.7086. Min Act: -0.0000

Data Index: 551495 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1140259 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.6749. Min Act: -0.0000

Data Index: 1115827 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.6722. Min Act: 0.0000

Data Index: 678794 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.6593. Min Act: -0.0000

Data Index: 638570 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.6505. Min Act: -0.0000

Data Index: 648028 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.6036. Min Act: -0.0000

Data Index: 859018 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.5572. Min Act: -0.0000

Data Index: 578377 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1054639 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.4481. Min Act: -0.0000

Data Index: 688646 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.5300. Min Act: -0.0000

Data Index: 873074 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1039638 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 2.2822. Min Range: -2.2822

Max Act: 1.4903. Min Act: -0.0000

Data Index: 529738 (C4 (Web Text))

Max Activating Token Index: 171