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

Dataset: The Pile

Neuron 437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.9572. Min Act: -0.0000

Data Index: 803954 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.9858. Min Act: -0.0000

Data Index: 774831 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.0015. Min Range: -1.0015

Max Act: 1.0015. Min Act: -0.0000

Data Index: 634638 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1650847 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7637. Min Act: -0.0000

Data Index: 530269 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1613608 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1350386 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6177. Min Act: -0.0000

Data Index: 770990 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.6010. Min Act: 0.0000

Data Index: 955388 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1361809 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1631282 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1337149 (The Pile)

Max Activating Token Index: 871

Text #12

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5500. Min Act: 0.0000

Data Index: 719617 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5170. Min Act: 0.0000

Data Index: 1760585 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5545. Min Act: -0.0000

Data Index: 51143 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1920048 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1155588 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1725279 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5034. Min Act: -0.0000

Data Index: 1683910 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 1.0015. Min Range: -1.0015

Max Act: 0.5147. Min Act: 0.0000

Data Index: 1388181 (The Pile)

Max Activating Token Index: 792