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

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

Neuron 5994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1434378 (Python Code)

Max Activating Token Index: 871

Text #1

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2245. Min Act: -0.0000

Data Index: 831267 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2033. Min Act: -0.0000

Data Index: 217814 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2086. Min Act: -0.0000

Data Index: 661418 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1155971 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1789. Min Act: -0.0000

Data Index: 514811 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1614284 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1352758 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1469225 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1820. Min Act: -0.0000

Data Index: 729010 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1281303 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1713. Min Act: -0.0000

Data Index: 470028 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1753. Min Act: -0.0000

Data Index: 610137 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1087168 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1413459 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1531. Min Act: -0.0000

Data Index: 123830 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1566. Min Act: -0.0000

Data Index: 927695 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1592. Min Act: -0.0000

Data Index: 935537 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1200614 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.3354. Min Range: -0.3354

Max Act: 0.1619. Min Act: -0.0000

Data Index: 90244 (C4 (Web Text))

Max Activating Token Index: 373