Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4349 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1585174 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1156505 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1677576 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1658. Min Act: -0.0000

Data Index: 703654 (The Pile)

Max Activating Token Index: 979

Text #4

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1131350 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1822. Min Act: -0.0000

Data Index: 948858 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1941026 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1652. Min Act: -0.0000

Data Index: 808662 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1583. Min Act: -0.0000

Data Index: 1489890 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1500279 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1634. Min Act: -0.0000

Data Index: 186999 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1051948 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1548139 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1481. Min Act: -0.0000

Data Index: 555599 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1635. Min Act: -0.0000

Data Index: 507431 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1481. Min Act: -0.0000

Data Index: 89043 (The Pile)

Max Activating Token Index: 79

Text #16

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1129771 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1803. Min Act: -0.0000

Data Index: 85817 (The Pile)

Max Activating Token Index: 793

Text #18

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1591188 (The Pile)

Max Activating Token Index: 954

Text #19

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1798. Min Act: -0.0000

Data Index: 220353 (The Pile)

Max Activating Token Index: 939