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

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

Neuron 721 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1455633 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1508865 (Python Code)

Max Activating Token Index: 733

Text #2

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1656150 (Python Code)

Max Activating Token Index: 477

Text #3

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1433674 (Python Code)

Max Activating Token Index: 518

Text #4

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1376620 (Python Code)

Max Activating Token Index: 324

Text #5

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.3206. Min Act: -0.0000

Data Index: 1363770 (Python Code)

Max Activating Token Index: 734

Text #6

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1517685 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1612766 (Python Code)

Max Activating Token Index: 978

Text #8

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1471979 (Python Code)

Max Activating Token Index: 1005

Text #9

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1609647 (Python Code)

Max Activating Token Index: 705

Text #10

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1199774 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1640761 (Python Code)

Max Activating Token Index: 868

Text #12

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1624312 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1705. Min Act: -0.0000

Data Index: 958046 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1499104 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1801. Min Act: -0.0000

Data Index: 915694 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1697. Min Act: -0.0000

Data Index: 1551139 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1689. Min Act: -0.0000

Data Index: 1495718 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1579. Min Act: -0.0000

Data Index: 352078 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.5049. Min Range: -0.5049

Max Act: 0.1677. Min Act: -0.0000

Data Index: 175927 (C4 (Web Text))

Max Activating Token Index: 969