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

Dataset: The Pile

Neuron 1092 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: 0.7599. Min Range: -0.7599

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1852907 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7554. Min Act: -0.0000

Data Index: 566524 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1447028 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1005911 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1033931 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1514429 (The Pile)

Max Activating Token Index: 961

Text #6

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1698520 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7230. Min Act: -0.0000

Data Index: 786467 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1943165 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1854751 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1948792 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6853. Min Act: -0.0000

Data Index: 615498 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1433737 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1538294 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6623. Min Act: -0.0000

Data Index: 320851 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1491247 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6323. Min Act: -0.0000

Data Index: 814566 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1000898 (The Pile)

Max Activating Token Index: 965

Text #18

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6933. Min Act: -0.0000

Data Index: 391824 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6904. Min Act: -0.0000

Data Index: 876321 (The Pile)

Max Activating Token Index: 168