Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1751 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.2195. Min Act: -0.0001

Data Index: 612127 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1923. Min Act: -0.0001

Data Index: 498251 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1977. Min Act: -0.0000

Data Index: 838570 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1871. Min Act: -0.0000

Data Index: 476431 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1177912 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1829. Min Act: -0.0000

Data Index: 917769 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1261554 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1672. Min Act: -0.0000

Data Index: 87480 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1192257 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1699. Min Act: -0.0000

Data Index: 33005 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1349922 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1299535 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1626. Min Act: -0.0001

Data Index: 364776 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1093841 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1544. Min Act: -0.0000

Data Index: 1216087 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1642. Min Act: -0.0000

Data Index: 696229 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1629. Min Act: -0.0000

Data Index: 872118 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1608. Min Act: -0.0001

Data Index: 264228 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1606. Min Act: -0.0000

Data Index: 354026 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.2195. Min Range: -0.2195

Max Act: 0.1666. Min Act: -0.0000

Data Index: 364205 (C4 (Web Text))

Max Activating Token Index: 989