Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1463. Min Range: -3.1463

Max Act: 3.1463. Min Act: -0.0000

Data Index: 21523 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.8295. Min Act: -0.0000

Data Index: 225285 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.7657. Min Act: -0.0000

Data Index: 934433 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.7273. Min Act: -0.0000

Data Index: 742920 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.5139. Min Act: -0.0000

Data Index: 742840 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.3750. Min Act: -0.0000

Data Index: 1137771 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.2211. Min Act: -0.0000

Data Index: 36805 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.0675. Min Act: -0.0000

Data Index: 391604 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.1898. Min Act: -0.0000

Data Index: 814348 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.1456. Min Act: -0.0000

Data Index: 219960 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.0035. Min Act: -0.0000

Data Index: 298742 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.0878. Min Act: -0.0000

Data Index: 1057633 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.0768. Min Act: -0.0000

Data Index: 662804 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.1463. Min Range: -3.1463

Max Act: 1.8225. Min Act: -0.0000

Data Index: 1246329 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.1153. Min Act: -0.0000

Data Index: 563330 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.0927. Min Act: -0.0000

Data Index: 251828 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 3.1463. Min Range: -3.1463

Max Act: 2.0633. Min Act: -0.0000

Data Index: 821563 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.1463. Min Range: -3.1463

Max Act: 1.7311. Min Act: -0.0000

Data Index: 1295353 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 3.1463. Min Range: -3.1463

Max Act: 1.9857. Min Act: -0.0000

Data Index: 881082 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.1463. Min Range: -3.1463

Max Act: 1.8308. Min Act: -0.0000

Data Index: 1333047 (C4 (Web Text))

Max Activating Token Index: 900