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

Dataset: The Pile

Neuron 26 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1750. Min Act: 0.0000

Data Index: 750859 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1705. Min Act: -0.0000

Data Index: 497270 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1697. Min Act: -0.0000

Data Index: 113389 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1803890 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1607. Min Act: -0.0000

Data Index: 430877 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1524. Min Act: -0.0000

Data Index: 525027 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1520. Min Act: -0.0000

Data Index: 662388 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1786908 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1506. Min Act: -0.0000

Data Index: 157362 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1814851 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1494. Min Act: -0.0000

Data Index: 347623 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1493. Min Act: -0.0000

Data Index: 1145858 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1326435 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1616848 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1054884 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1512613 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1510. Min Act: -0.0000

Data Index: 904786 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1454. Min Act: -0.0000

Data Index: 343975 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1075920 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1427. Min Act: -0.0000

Data Index: 876233 (The Pile)

Max Activating Token Index: 1023