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

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

Neuron 415 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.3060. Min Act: -0.0001

Data Index: 753495 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2643. Min Act: -0.0001

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2370. Min Act: -0.0001

Data Index: 1313491 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2153. Min Act: -0.0001

Data Index: 817775 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2276. Min Act: -0.0001

Data Index: 676833 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2047. Min Act: -0.0001

Data Index: 207560 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1907. Min Act: -0.0001

Data Index: 806770 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1869. Min Act: -0.0001

Data Index: 791584 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1786. Min Act: -0.0001

Data Index: 826419 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1789. Min Act: -0.0001

Data Index: 622787 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.2251. Min Act: -0.0001

Data Index: 966601 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1735. Min Act: -0.0001

Data Index: 536564 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1860. Min Act: -0.0001

Data Index: 358729 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1035030 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1763. Min Act: -0.0001

Data Index: 302415 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1651. Min Act: -0.0001

Data Index: 3463 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1895. Min Act: -0.0001

Data Index: 471308 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1077320 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1686. Min Act: -0.0001

Data Index: 952943 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.3060. Min Range: -0.3060

Max Act: 0.1673. Min Act: -0.0001

Data Index: 731531 (C4 (Web Text))

Max Activating Token Index: 659