Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 227 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.9507. Min Act: -0.0000

Data Index: 1594972 (Python Code)

Max Activating Token Index: 56

Text #1

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.6510. Min Act: -0.0000

Data Index: 1578773 (Python Code)

Max Activating Token Index: 641

Text #2

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.6509. Min Act: -0.0000

Data Index: 1377575 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.3812. Min Act: -0.0000

Data Index: 1555053 (Python Code)

Max Activating Token Index: 1005

Text #4

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.4756. Min Act: -0.0000

Data Index: 1618472 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.4212. Min Act: -0.0000

Data Index: 1548790 (Python Code)

Max Activating Token Index: 909

Text #6

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.4007. Min Act: -0.0000

Data Index: 1444533 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.4014. Min Act: -0.0000

Data Index: 1652083 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.2265. Min Act: -0.0000

Data Index: 1525002 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.2319. Min Act: -0.0000

Data Index: 1500829 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.5485. Min Act: -0.0000

Data Index: 1511529 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.5245. Min Act: -0.0000

Data Index: 1468914 (Python Code)

Max Activating Token Index: 506

Text #12

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.3665. Min Act: -0.0000

Data Index: 1387388 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.0544. Min Act: -0.0000

Data Index: 1428468 (Python Code)

Max Activating Token Index: 795

Text #14

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.0676. Min Act: -0.0000

Data Index: 1576516 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.3579. Min Act: -0.0000

Data Index: 1371010 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.3570. Min Act: -0.0000

Data Index: 1564719 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.3518. Min Act: -0.0000

Data Index: 1612019 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.3497. Min Act: -0.0000

Data Index: 1632065 (Python Code)

Max Activating Token Index: 808

Text #19

Max Range: 3.9507. Min Range: -3.9507

Max Act: 3.3017. Min Act: -0.0000

Data Index: 1494559 (Python Code)

Max Activating Token Index: 8