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

Dataset: The Pile

Neuron 1863 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: 1.9508. Min Range: -1.9508

Max Act: 1.9393. Min Act: -0.0000

Data Index: 1695799 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.8288. Min Act: -0.0000

Data Index: 663719 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.9508. Min Act: -0.0000

Data Index: 1764336 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.6544. Min Act: -0.0000

Data Index: 562573 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1226949 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1039438 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.5904. Min Act: -0.0000

Data Index: 817130 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.6127. Min Act: -0.0000

Data Index: 923244 (The Pile)

Max Activating Token Index: 19

Text #8

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.7086. Min Act: -0.0000

Data Index: 248404 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.6166. Min Act: -0.0000

Data Index: 607200 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.6048. Min Act: -0.0000

Data Index: 379502 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1245970 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.5251. Min Act: -0.0000

Data Index: 431195 (The Pile)

Max Activating Token Index: 746

Text #13

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.3150. Min Act: -0.0000

Data Index: 209874 (The Pile)

Max Activating Token Index: 841

Text #14

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1077393 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1941659 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1767369 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.6482. Min Act: -0.0000

Data Index: 1889517 (The Pile)

Max Activating Token Index: 939

Text #18

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.4574. Min Act: -0.0000

Data Index: 659268 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 1.9508. Min Range: -1.9508

Max Act: 1.5240. Min Act: -0.0000

Data Index: 890413 (The Pile)

Max Activating Token Index: 426