Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3545 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1142718 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1242561 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1292136 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 1.1087. Min Range: -1.1087

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1349976 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9590. Min Act: -0.0001

Data Index: 3424 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.9231. Min Act: -0.0001

Data Index: 218672 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8938. Min Act: -0.0000

Data Index: 273478 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8598. Min Act: -0.0001

Data Index: 748804 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8271. Min Act: -0.0001

Data Index: 389455 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.8038. Min Act: -0.0000

Data Index: 781993 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7783. Min Act: -0.0000

Data Index: 782957 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7690. Min Act: -0.0000

Data Index: 871349 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7654. Min Act: -0.0000

Data Index: 781437 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7799. Min Act: -0.0000

Data Index: 102541 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7780. Min Act: -0.0000

Data Index: 459679 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7706. Min Act: -0.0000

Data Index: 424744 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7645. Min Act: -0.0000

Data Index: 567983 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7493. Min Act: -0.0000

Data Index: 590891 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.6652. Min Act: -0.0001

Data Index: 372487 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.1087. Min Range: -1.1087

Max Act: 0.7722. Min Act: -0.0000

Data Index: 448368 (C4 (Web Text))

Max Activating Token Index: 199