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

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

Neuron 5880 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1839. Min Range: -4.1839

Max Act: 4.1407. Min Act: -0.0000

Data Index: 1652530 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 4.1839. Min Range: -4.1839

Max Act: 4.1839. Min Act: -0.0000

Data Index: 1498807 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.9338. Min Act: -0.0000

Data Index: 1533631 (Python Code)

Max Activating Token Index: 668

Text #3

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.9063. Min Act: -0.0000

Data Index: 1637304 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.6465. Min Act: -0.0000

Data Index: 1364847 (Python Code)

Max Activating Token Index: 905

Text #5

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.6374. Min Act: -0.0000

Data Index: 1555711 (Python Code)

Max Activating Token Index: 843

Text #6

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.7335. Min Act: -0.0000

Data Index: 1538937 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.2548. Min Act: -0.0000

Data Index: 1495444 (Python Code)

Max Activating Token Index: 964

Text #8

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.4823. Min Act: -0.0000

Data Index: 1612398 (Python Code)

Max Activating Token Index: 889

Text #9

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.6428. Min Act: -0.0000

Data Index: 1646633 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.4738. Min Act: -0.0000

Data Index: 1498776 (Python Code)

Max Activating Token Index: 595

Text #11

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.2758. Min Act: -0.0000

Data Index: 1605872 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.1715. Min Act: -0.0000

Data Index: 1564970 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.3375. Min Act: -0.0000

Data Index: 1596283 (Python Code)

Max Activating Token Index: 672

Text #14

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.6102. Min Act: -0.0000

Data Index: 1438158 (Python Code)

Max Activating Token Index: 693

Text #15

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.4663. Min Act: -0.0000

Data Index: 1423334 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.4122. Min Act: -0.0000

Data Index: 1413318 (Python Code)

Max Activating Token Index: 833

Text #17

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.1901. Min Act: -0.0000

Data Index: 1512708 (Python Code)

Max Activating Token Index: 812

Text #18

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.1796. Min Act: -0.0000

Data Index: 1499616 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 4.1839. Min Range: -4.1839

Max Act: 3.4683. Min Act: -0.0000

Data Index: 1636815 (Python Code)

Max Activating Token Index: 698