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

Dataset: The Pile

Neuron 4622 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: 0.7609. Min Range: -0.7609

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1054882 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.7100. Min Act: -0.0000

Data Index: 204249 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6242. Min Act: -0.0000

Data Index: 321270 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1430369 (The Pile)

Max Activating Token Index: 605

Text #4

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1526635 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6126. Min Act: -0.0000

Data Index: 352143 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1690040 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1042035 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1836709 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1462897 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1031250 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5654. Min Act: -0.0000

Data Index: 715790 (The Pile)

Max Activating Token Index: 554

Text #12

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.6212. Min Act: -0.0000

Data Index: 214306 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1071128 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1519939 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5265. Min Act: -0.0000

Data Index: 992542 (The Pile)

Max Activating Token Index: 20

Text #16

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5322. Min Act: -0.0000

Data Index: 80055 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.5176. Min Act: -0.0000

Data Index: 121837 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.4999. Min Act: -0.0000

Data Index: 328934 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.7609. Min Range: -0.7609

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1093807 (The Pile)

Max Activating Token Index: 373