Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2956 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1386758 (Python Code)

Max Activating Token Index: 214

Text #1

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2385. Min Act: 0.0000

Data Index: 1646903 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1408215 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1573831 (Python Code)

Max Activating Token Index: 727

Text #4

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1467390 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1559670 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1913. Min Act: -0.0001

Data Index: 1492001 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1841. Min Act: 0.0000

Data Index: 1372748 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1888. Min Act: -0.0000

Data Index: 1479888 (Python Code)

Max Activating Token Index: 312

Text #9

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1525. Min Act: 0.0001

Data Index: 1633908 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1374110 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1504460 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1710. Min Act: 0.0001

Data Index: 1427867 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1688. Min Act: 0.0001

Data Index: 1388149 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1741. Min Act: 0.0001

Data Index: 1426151 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1474510 (Python Code)

Max Activating Token Index: 268

Text #16

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1723. Min Act: 0.0001

Data Index: 1505139 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1460858 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1567506 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 0.2704. Min Range: -0.2704

Max Act: 0.1702. Min Act: 0.0001

Data Index: 1648701 (Python Code)

Max Activating Token Index: 7