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

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

Neuron 477 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2315. Min Act: -0.0001

Data Index: 775079 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2002. Min Act: -0.0002

Data Index: 741958 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2016. Min Act: -0.0002

Data Index: 477695 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1910. Min Act: -0.0002

Data Index: 483452 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1857. Min Act: -0.0002

Data Index: 425744 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1598. Min Act: -0.0002

Data Index: 856086 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1763. Min Act: -0.0002

Data Index: 542212 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1802. Min Act: -0.0002

Data Index: 155787 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1946. Min Act: -0.0002

Data Index: 584315 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1848. Min Act: -0.0002

Data Index: 1215049 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1774. Min Act: -0.0002

Data Index: 599623 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.2041. Min Act: -0.0002

Data Index: 594480 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1842. Min Act: -0.0002

Data Index: 1217538 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1463. Min Act: -0.0002

Data Index: 766178 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1817. Min Act: -0.0001

Data Index: 13258 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1798. Min Act: -0.0002

Data Index: 1017698 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1996. Min Act: -0.0001

Data Index: 429619 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1649. Min Act: -0.0002

Data Index: 1255585 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1892. Min Act: -0.0001

Data Index: 191190 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2315. Min Range: -0.2315

Max Act: 0.1630. Min Act: -0.0002

Data Index: 861370 (C4 (Web Text))

Max Activating Token Index: 247