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

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

Neuron 3472 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.8534. Min Act: -0.0000

Data Index: 598430 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.8102. Min Act: -0.0001

Data Index: 1187806 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7711. Min Act: -0.0000

Data Index: 474065 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1170798 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.8083. Min Act: -0.0001

Data Index: 684759 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6576. Min Act: -0.0001

Data Index: 617441 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6805. Min Act: -0.0000

Data Index: 261241 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6848. Min Act: -0.0000

Data Index: 489060 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6721. Min Act: -0.0001

Data Index: 18466 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6241. Min Act: -0.0001

Data Index: 279536 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6690. Min Act: -0.0000

Data Index: 1276952 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6463. Min Act: -0.0001

Data Index: 22179 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6446. Min Act: -0.0001

Data Index: 124694 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6430. Min Act: -0.0000

Data Index: 697619 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6182. Min Act: -0.0000

Data Index: 265507 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1293414 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6051. Min Act: -0.0001

Data Index: 436506 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5863. Min Act: -0.0001

Data Index: 90132 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6241. Min Act: -0.0001

Data Index: 1051147 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6244. Min Act: -0.0001

Data Index: 1321163 (C4 (Web Text))

Max Activating Token Index: 67