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

Dataset: The Pile

Neuron 1273 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1204189 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1821447 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1564493 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1269000 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1769470 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1578466 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8065. Min Act: -0.0000

Data Index: 621721 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1447021 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1244919 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7839. Min Act: -0.0000

Data Index: 381724 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8011. Min Act: -0.0000

Data Index: 732348 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1946453 (The Pile)

Max Activating Token Index: 572

Text #12

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7859. Min Act: -0.0000

Data Index: 933027 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8217. Min Act: -0.0000

Data Index: 252255 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7776. Min Act: -0.0000

Data Index: 992179 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7913. Min Act: -0.0000

Data Index: 66444 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7916. Min Act: -0.0000

Data Index: 889890 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1962450 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1979190 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 0.9055. Min Range: -0.9055

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1107908 (The Pile)

Max Activating Token Index: 843