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

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

Neuron 3211 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: 6.4702. Min Range: -6.4702

Max Act: 6.4702. Min Act: -0.0000

Data Index: 1432449 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 6.4702. Min Range: -6.4702

Max Act: 6.0719. Min Act: -0.0000

Data Index: 1640854 (Python Code)

Max Activating Token Index: 315

Text #2

Max Range: 6.4702. Min Range: -6.4702

Max Act: 6.1852. Min Act: -0.0000

Data Index: 1639636 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.7482. Min Act: -0.0000

Data Index: 1591687 (Python Code)

Max Activating Token Index: 596

Text #4

Max Range: 6.4702. Min Range: -6.4702

Max Act: 6.0839. Min Act: -0.0000

Data Index: 1427591 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 6.4702. Min Range: -6.4702

Max Act: 6.1248. Min Act: -0.0000

Data Index: 1589939 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.8877. Min Act: -0.0000

Data Index: 1565724 (Python Code)

Max Activating Token Index: 325

Text #7

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.8113. Min Act: -0.0000

Data Index: 1426548 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.7116. Min Act: -0.0000

Data Index: 1497791 (Python Code)

Max Activating Token Index: 19

Text #9

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.4731. Min Act: -0.0000

Data Index: 1587670 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.6162. Min Act: -0.0000

Data Index: 404702 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.5216. Min Act: -0.0000

Data Index: 1362545 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.7739. Min Act: -0.0000

Data Index: 1541304 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.3852. Min Act: -0.0000

Data Index: 1465462 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.5753. Min Act: -0.0000

Data Index: 828266 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.7060. Min Act: -0.0000

Data Index: 1552746 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.2922. Min Act: -0.0000

Data Index: 1523128 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.5976. Min Act: -0.0000

Data Index: 1490098 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.5575. Min Act: -0.0000

Data Index: 1426802 (Python Code)

Max Activating Token Index: 332

Text #19

Max Range: 6.4702. Min Range: -6.4702

Max Act: 5.3516. Min Act: -0.0000

Data Index: 1370460 (Python Code)

Max Activating Token Index: 197