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

Dataset: The Pile

Neuron 665 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: 0.7023. Min Range: -0.7023

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1355190 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.7023. Min Act: -0.0000

Data Index: 947443 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1509058 (The Pile)

Max Activating Token Index: 80

Text #3

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1789055 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1865365 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1659262 (The Pile)

Max Activating Token Index: 88

Text #6

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1955372 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1488323 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6225. Min Act: -0.0000

Data Index: 477694 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6422. Min Act: -0.0000

Data Index: 503109 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6553. Min Act: -0.0000

Data Index: 298092 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1565324 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6342. Min Act: -0.0000

Data Index: 744781 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.5774. Min Act: -0.0000

Data Index: 894984 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1359400 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6596. Min Act: -0.0000

Data Index: 227307 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1988733 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6078. Min Act: -0.0000

Data Index: 860735 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.5726. Min Act: -0.0000

Data Index: 494658 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.5665. Min Act: -0.0000

Data Index: 1804733 (The Pile)

Max Activating Token Index: 756