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

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

Neuron 3427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1494956 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1411944 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1498200 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1391685 (Python Code)

Max Activating Token Index: 974

Text #4

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1624786 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1444443 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.6063. Min Act: -0.0000

Data Index: 874190 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1507001 (Python Code)

Max Activating Token Index: 764

Text #8

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1400534 (Python Code)

Max Activating Token Index: 572

Text #9

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1430584 (Python Code)

Max Activating Token Index: 688

Text #10

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1599925 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1594224 (Python Code)

Max Activating Token Index: 208

Text #12

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1535868 (Python Code)

Max Activating Token Index: 654

Text #13

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1157774 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1497778 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5348. Min Act: -0.0000

Data Index: 1648504 (Python Code)

Max Activating Token Index: 385

Text #16

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1518559 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1204407 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1654185 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 0.6779. Min Range: -0.6779

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1039244 (C4 (Web Text))

Max Activating Token Index: 857