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

Dataset: The Pile

Neuron 4456 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1551381 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5286. Min Act: -0.0000

Data Index: 945891 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5186. Min Act: -0.0000

Data Index: 477272 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1114684 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4971. Min Act: -0.0000

Data Index: 595256 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1253049 (The Pile)

Max Activating Token Index: 615

Text #6

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4957. Min Act: -0.0000

Data Index: 155047 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1666892 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4683. Min Act: -0.0000

Data Index: 773551 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4529. Min Act: -0.0000

Data Index: 595343 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1838288 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4458. Min Act: -0.0000

Data Index: 226140 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1293544 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1549662 (The Pile)

Max Activating Token Index: 55

Text #14

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1130135 (The Pile)

Max Activating Token Index: 535

Text #15

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1935368 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4468. Min Act: -0.0000

Data Index: 287909 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4443. Min Act: -0.0000

Data Index: 571834 (The Pile)

Max Activating Token Index: 454

Text #18

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4561. Min Act: -0.0000

Data Index: 445314 (The Pile)

Max Activating Token Index: 61

Text #19

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4472. Min Act: -0.0000

Data Index: 718315 (The Pile)

Max Activating Token Index: 545