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

Dataset: The Pile

Neuron 2744 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: 1.4813. Min Range: -1.4813

Max Act: 1.4813. Min Act: -0.0000

Data Index: 1345115 (The Pile)

Max Activating Token Index: 610

Text #1

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2206. Min Act: -0.0000

Data Index: 1064493 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1985. Min Act: -0.0000

Data Index: 1881938 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1137. Min Act: -0.0000

Data Index: 1644875 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1883. Min Act: -0.0000

Data Index: 1304581 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2027. Min Act: -0.0000

Data Index: 391472 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1611772 (The Pile)

Max Activating Token Index: 544

Text #7

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0975. Min Act: -0.0000

Data Index: 303305 (The Pile)

Max Activating Token Index: 367

Text #8

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1537532 (The Pile)

Max Activating Token Index: 143

Text #9

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1000005 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0878. Min Act: -0.0000

Data Index: 891743 (The Pile)

Max Activating Token Index: 855

Text #11

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1045. Min Act: -0.0000

Data Index: 1530162 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0614. Min Act: -0.0000

Data Index: 487373 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1205. Min Act: -0.0000

Data Index: 1442052 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1635500 (The Pile)

Max Activating Token Index: 563

Text #15

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1666859 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0451. Min Act: -0.0000

Data Index: 663360 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.4813. Min Range: -1.4813

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1746369 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1063. Min Act: -0.0000

Data Index: 853318 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.0394. Min Act: -0.0000

Data Index: 12667 (The Pile)

Max Activating Token Index: 588