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

Dataset: The Pile

Neuron 2495 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.5583. Min Act: -0.0000

Data Index: 1715298 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.1524. Min Act: -0.0000

Data Index: 676714 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1048217 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1257465 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1021091 (The Pile)

Max Activating Token Index: 730

Text #5

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.0118. Min Act: -0.0000

Data Index: 1781058 (The Pile)

Max Activating Token Index: 382

Text #6

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9836. Min Act: 0.0001

Data Index: 865695 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1852558 (The Pile)

Max Activating Token Index: 902

Text #8

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9079. Min Act: 0.0000

Data Index: 1615369 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 1.5583. Min Range: -1.5583

Max Act: 1.0110. Min Act: -0.0000

Data Index: 574201 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9220. Min Act: -0.0000

Data Index: 936153 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9197. Min Act: 0.0000

Data Index: 1106028 (The Pile)

Max Activating Token Index: 763

Text #12

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.8946. Min Act: 0.0000

Data Index: 595912 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1167304 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1250030 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1619570 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9189. Min Act: -0.0000

Data Index: 302181 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.9128. Min Act: -0.0000

Data Index: 779654 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1211368 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 1.5583. Min Range: -1.5583

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1094878 (The Pile)

Max Activating Token Index: 441