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

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

Neuron 1167 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3450. Min Range: -3.3450

Max Act: 3.2357. Min Act: -0.0000

Data Index: 704302 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 3.3450. Min Range: -3.3450

Max Act: 3.3450. Min Act: -0.0000

Data Index: 1426641 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 3.3450. Min Range: -3.3450

Max Act: 3.3199. Min Act: -0.0000

Data Index: 1169743 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 3.3450. Min Range: -3.3450

Max Act: 3.2002. Min Act: -0.0000

Data Index: 1205561 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 3.3450. Min Range: -3.3450

Max Act: 3.1411. Min Act: -0.0000

Data Index: 982043 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.9666. Min Act: -0.0000

Data Index: 1141117 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.9532. Min Act: -0.0000

Data Index: 1065075 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.6573. Min Act: -0.0000

Data Index: 1433396 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.7837. Min Act: -0.0000

Data Index: 1558711 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.6733. Min Act: -0.0000

Data Index: 1515066 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.6596. Min Act: -0.0000

Data Index: 1585951 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.5284. Min Act: -0.0000

Data Index: 1530489 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.4843. Min Act: -0.0000

Data Index: 1426761 (Python Code)

Max Activating Token Index: 657

Text #13

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.5918. Min Act: -0.0000

Data Index: 1590694 (Python Code)

Max Activating Token Index: 472

Text #14

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.5407. Min Act: -0.0000

Data Index: 1494960 (Python Code)

Max Activating Token Index: 756

Text #15

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.4015. Min Act: -0.0000

Data Index: 1650391 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.3743. Min Act: -0.0000

Data Index: 1520389 (Python Code)

Max Activating Token Index: 601

Text #17

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.5830. Min Act: -0.0000

Data Index: 1447037 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1382867 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 3.3450. Min Range: -3.3450

Max Act: 2.5257. Min Act: -0.0000

Data Index: 1619922 (Python Code)

Max Activating Token Index: 176