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

Dataset: The Pile

Neuron 1777 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3901. Min Range: -5.3901

Max Act: 5.3901. Min Act: -0.0000

Data Index: 671798 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.2517. Min Act: -0.0000

Data Index: 1392259 (The Pile)

Max Activating Token Index: 3

Text #2

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.0986. Min Act: -0.0000

Data Index: 735487 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.1160. Min Act: -0.0000

Data Index: 820795 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.1036. Min Act: -0.0000

Data Index: 246095 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.9018. Min Act: -0.0000

Data Index: 104564 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.0263. Min Act: -0.0000

Data Index: 1529410 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.1753. Min Act: -0.0000

Data Index: 1977532 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.0032. Min Act: -0.0000

Data Index: 1169430 (The Pile)

Max Activating Token Index: 555

Text #9

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.9873. Min Act: -0.0000

Data Index: 1345715 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.9787. Min Act: -0.0000

Data Index: 1775707 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 5.3901. Min Range: -5.3901

Max Act: 4.1514. Min Act: -0.0000

Data Index: 382086 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.9264. Min Act: -0.0000

Data Index: 1612208 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.9117. Min Act: -0.0000

Data Index: 1822066 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.8743. Min Act: -0.0000

Data Index: 1958813 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.7050. Min Act: -0.0000

Data Index: 876142 (The Pile)

Max Activating Token Index: 665

Text #16

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.9957. Min Act: -0.0000

Data Index: 1725932 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.7899. Min Act: -0.0000

Data Index: 516943 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.7965. Min Act: -0.0000

Data Index: 1383939 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 5.3901. Min Range: -5.3901

Max Act: 3.9122. Min Act: -0.0000

Data Index: 1156926 (The Pile)

Max Activating Token Index: 4