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

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

Neuron 6062 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: 1.4534. Min Range: -1.4534

Max Act: 1.4534. Min Act: -0.0000

Data Index: 129545 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 1.4534. Min Range: -1.4534

Max Act: 1.2904. Min Act: -0.0000

Data Index: 445870 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 1.4534. Min Range: -1.4534

Max Act: 1.0436. Min Act: -0.0000

Data Index: 596628 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 1.4534. Min Range: -1.4534

Max Act: 1.0566. Min Act: -0.0000

Data Index: 682770 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.4534. Min Range: -1.4534

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1040383 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 1.4534. Min Range: -1.4534

Max Act: 1.0570. Min Act: -0.0000

Data Index: 364849 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.9076. Min Act: -0.0000

Data Index: 483367 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8543. Min Act: -0.0000

Data Index: 125509 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8795. Min Act: -0.0000

Data Index: 623701 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1242621 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8242. Min Act: -0.0000

Data Index: 270874 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.7973. Min Act: -0.0000

Data Index: 545454 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1253326 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1056904 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.7667. Min Act: -0.0000

Data Index: 584852 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8124. Min Act: -0.0000

Data Index: 878711 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.8918. Min Act: -0.0000

Data Index: 773926 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.7917. Min Act: -0.0000

Data Index: 823227 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.7766. Min Act: -0.0000

Data Index: 344420 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.4534. Min Range: -1.4534

Max Act: 0.7615. Min Act: -0.0000

Data Index: 439350 (C4 (Web Text))

Max Activating Token Index: 202