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

Dataset: The Pile

Neuron 5080 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: 0.6703. Min Range: -0.6703

Max Act: 0.6703. Min Act: -0.0000

Data Index: 610084 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1800358 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5540. Min Act: -0.0000

Data Index: 30883 (The Pile)

Max Activating Token Index: 324

Text #3

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1936208 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1858377 (The Pile)

Max Activating Token Index: 599

Text #5

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5141. Min Act: -0.0000

Data Index: 625077 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1417816 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1443429 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1006397 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1518191 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1476380 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1409650 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1815423 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1472951 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4601. Min Act: -0.0000

Data Index: 366068 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1816385 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5163. Min Act: -0.0000

Data Index: 330652 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5152. Min Act: -0.0000

Data Index: 664750 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1942400 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1176016 (The Pile)

Max Activating Token Index: 181