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

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

Neuron 5485 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5731. Min Range: -7.5731

Max Act: 7.5731. Min Act: -0.0000

Data Index: 1403769 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.5711. Min Act: -0.0000

Data Index: 1361378 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.6419. Min Act: -0.0000

Data Index: 1584507 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.6436. Min Act: -0.0000

Data Index: 1546596 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 7.5731. Min Range: -7.5731

Max Act: 6.0511. Min Act: -0.0000

Data Index: 1523957 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.6837. Min Act: -0.0000

Data Index: 1387721 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.3629. Min Act: -0.0000

Data Index: 1426436 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.3822. Min Act: -0.0000

Data Index: 1563427 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.5800. Min Act: -0.0000

Data Index: 1604019 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.3994. Min Act: -0.0000

Data Index: 1607956 (Python Code)

Max Activating Token Index: 500

Text #10

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.2830. Min Act: -0.0000

Data Index: 1579918 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.2473. Min Act: -0.0000

Data Index: 1364076 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.2286. Min Act: -0.0000

Data Index: 1560538 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.3874. Min Act: -0.0000

Data Index: 1494571 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.1681. Min Act: -0.0000

Data Index: 1388010 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.2086. Min Act: -0.0000

Data Index: 1366852 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.0444. Min Act: -0.0000

Data Index: 1450687 (Python Code)

Max Activating Token Index: 97

Text #17

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.3936. Min Act: -0.0000

Data Index: 1464006 (Python Code)

Max Activating Token Index: 767

Text #18

Max Range: 7.5731. Min Range: -7.5731

Max Act: 4.7977. Min Act: -0.0000

Data Index: 1631838 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 7.5731. Min Range: -7.5731

Max Act: 5.2840. Min Act: -0.0000

Data Index: 1497599 (Python Code)

Max Activating Token Index: 578