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

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

Neuron 3691 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1760. Min Act: -0.0000

Data Index: 322536 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.2009. Min Act: -0.0000

Data Index: 282935 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1922. Min Act: -0.0000

Data Index: 200896 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1727. Min Act: -0.0001

Data Index: 216623 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1923. Min Act: -0.0000

Data Index: 872634 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1199740 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1841. Min Act: -0.0000

Data Index: 897579 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1851. Min Act: -0.0000

Data Index: 976720 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1693. Min Act: -0.0001

Data Index: 361574 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1615. Min Act: -0.0000

Data Index: 124606 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1723. Min Act: -0.0000

Data Index: 854175 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1704. Min Act: -0.0000

Data Index: 229698 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1602. Min Act: -0.0000

Data Index: 280286 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1599. Min Act: -0.0000

Data Index: 658234 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1535. Min Act: -0.0000

Data Index: 665522 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1243818 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1406. Min Act: -0.0000

Data Index: 252768 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1110388 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1541. Min Act: -0.0000

Data Index: 445201 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.2009. Min Range: -0.2009

Max Act: 0.1438. Min Act: -0.0000

Data Index: 43374 (C4 (Web Text))

Max Activating Token Index: 180