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

Dataset: The Pile

Neuron 2350 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: 1.0688. Min Range: -1.0688

Max Act: 1.0688. Min Act: -0.0000

Data Index: 233008 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1683134 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1994159 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.8408. Min Act: -0.0000

Data Index: 8201 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1316860 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7525. Min Act: -0.0000

Data Index: 235158 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7918. Min Act: -0.0000

Data Index: 73739 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7476. Min Act: -0.0000

Data Index: 323565 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7623. Min Act: -0.0000

Data Index: 317867 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1301007 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1063988 (The Pile)

Max Activating Token Index: 386

Text #11

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7231. Min Act: -0.0000

Data Index: 605324 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7615. Min Act: -0.0000

Data Index: 364319 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7440. Min Act: -0.0000

Data Index: 200456 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7398. Min Act: -0.0000

Data Index: 949148 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1697313 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.6995. Min Act: -0.0000

Data Index: 115086 (The Pile)

Max Activating Token Index: 79

Text #17

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1591328 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1952177 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 1.0688. Min Range: -1.0688

Max Act: 0.7102. Min Act: -0.0000

Data Index: 982724 (The Pile)

Max Activating Token Index: 608