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

Dataset: The Pile

Neuron 199 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: 3.3600. Min Range: -3.3600

Max Act: 3.3600. Min Act: -0.0000

Data Index: 376722 (The Pile)

Max Activating Token Index: 864

Text #1

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.1873. Min Act: -0.0000

Data Index: 904107 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.9855. Min Act: -0.0000

Data Index: 1236761 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.1111. Min Act: -0.0000

Data Index: 1116840 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.0951. Min Act: -0.0000

Data Index: 19392 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.0813. Min Act: -0.0000

Data Index: 1027254 (The Pile)

Max Activating Token Index: 713

Text #6

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.8668. Min Act: -0.0000

Data Index: 1942205 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.6213. Min Act: -0.0000

Data Index: 387266 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.0300. Min Act: -0.0000

Data Index: 352423 (The Pile)

Max Activating Token Index: 786

Text #9

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.5999. Min Act: -0.0000

Data Index: 1995270 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.8948. Min Act: -0.0000

Data Index: 248109 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.5812. Min Act: -0.0000

Data Index: 1811541 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.6410. Min Act: -0.0000

Data Index: 705500 (The Pile)

Max Activating Token Index: 643

Text #13

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.9184. Min Act: -0.0000

Data Index: 731092 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.7889. Min Act: -0.0000

Data Index: 881690 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.7627. Min Act: -0.0000

Data Index: 1120925 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.6994. Min Act: -0.0000

Data Index: 53185 (The Pile)

Max Activating Token Index: 197

Text #17

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.6068. Min Act: -0.0000

Data Index: 1057793 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.5864. Min Act: -0.0000

Data Index: 1932461 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.8444. Min Act: -0.0000

Data Index: 1975405 (The Pile)

Max Activating Token Index: 705