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

Dataset: The Pile

Neuron 645 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1168866 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5354. Min Act: -0.0000

Data Index: 244781 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4760. Min Act: -0.0000

Data Index: 695929 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4602. Min Act: -0.0000

Data Index: 994695 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1137759 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4594. Min Act: -0.0000

Data Index: 511032 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4138. Min Act: -0.0000

Data Index: 617741 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4336. Min Act: -0.0000

Data Index: 587545 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1484448 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1025295 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4263. Min Act: -0.0000

Data Index: 208312 (The Pile)

Max Activating Token Index: 143

Text #11

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1199180 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3808. Min Act: -0.0000

Data Index: 735013 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1990656 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4016. Min Act: -0.0000

Data Index: 199576 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4120. Min Act: -0.0000

Data Index: 534383 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3884. Min Act: -0.0000

Data Index: 632861 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4113. Min Act: -0.0000

Data Index: 704320 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.3962. Min Act: -0.0000

Data Index: 903386 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4226. Min Act: -0.0000

Data Index: 763130 (The Pile)

Max Activating Token Index: 33