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

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

Neuron 3879 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1810. Min Act: -0.0001

Data Index: 840010 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1190681 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1740. Min Act: -0.0001

Data Index: 147181 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1677. Min Act: -0.0001

Data Index: 228514 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1553. Min Act: -0.0001

Data Index: 377400 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1742. Min Act: -0.0001

Data Index: 50216 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1741. Min Act: -0.0001

Data Index: 580743 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1672. Min Act: -0.0001

Data Index: 850299 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1868. Min Act: -0.0001

Data Index: 582000 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1097744 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1121640 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1658. Min Act: -0.0001

Data Index: 624072 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1681. Min Act: -0.0001

Data Index: 452453 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1614. Min Act: -0.0001

Data Index: 102828 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1575. Min Act: -0.0001

Data Index: 202890 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1641. Min Act: -0.0001

Data Index: 6101 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1688. Min Act: -0.0001

Data Index: 665804 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1557. Min Act: -0.0001

Data Index: 39063 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1614. Min Act: -0.0001

Data Index: 681315 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1793. Min Act: -0.0001

Data Index: 890540 (C4 (Web Text))

Max Activating Token Index: 830