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

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

Neuron 2730 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0000

Data Index: 181624 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1070479 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1119797 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1242. Min Act: -0.0000

Data Index: 951324 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1049. Min Act: -0.0000

Data Index: 303473 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1011. Min Act: -0.0000

Data Index: 928987 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1019. Min Act: -0.0000

Data Index: 570660 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1023. Min Act: -0.0000

Data Index: 26832 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0976. Min Act: -0.0000

Data Index: 390757 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1322471 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0968. Min Act: -0.0000

Data Index: 727164 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0957. Min Act: -0.0000

Data Index: 587577 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1079959 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0968. Min Act: -0.0000

Data Index: 697010 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0923. Min Act: -0.0000

Data Index: 847367 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0948. Min Act: -0.0000

Data Index: 947450 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0894. Min Act: -0.0000

Data Index: 432897 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0961. Min Act: -0.0000

Data Index: 783905 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0912. Min Act: -0.0000

Data Index: 168383 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.0888. Min Act: -0.0001

Data Index: 496575 (C4 (Web Text))

Max Activating Token Index: 862