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

Dataset: The Pile

Neuron 1767 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.9742. Min Act: -0.0000

Data Index: 507554 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1342537 (The Pile)

Max Activating Token Index: 160

Text #2

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1822865 (The Pile)

Max Activating Token Index: 846

Text #3

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1540254 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6742. Min Act: -0.0000

Data Index: 565574 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6411. Min Act: -0.0000

Data Index: 517584 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6389. Min Act: -0.0000

Data Index: 98048 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1894725 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6692. Min Act: -0.0000

Data Index: 974327 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6697. Min Act: -0.0000

Data Index: 198066 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1211734 (The Pile)

Max Activating Token Index: 18

Text #11

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5577. Min Act: -0.0000

Data Index: 472867 (The Pile)

Max Activating Token Index: 588

Text #12

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1314906 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5997. Min Act: -0.0000

Data Index: 405324 (The Pile)

Max Activating Token Index: 297

Text #14

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5918. Min Act: -0.0000

Data Index: 915585 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1480084 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5601. Min Act: -0.0000

Data Index: 126138 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5365. Min Act: -0.0000

Data Index: 493608 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1742397 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1252172 (The Pile)

Max Activating Token Index: 648