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

Dataset: The Pile

Neuron 4267 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.7893. Min Act: -0.0000

Data Index: 133259 (The Pile)

Max Activating Token Index: 895

Text #1

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.9968. Min Act: -0.0000

Data Index: 1725792 (The Pile)

Max Activating Token Index: 216

Text #2

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.6692. Min Act: -0.0000

Data Index: 1498418 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.8781. Min Act: -0.0000

Data Index: 1741214 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.5998. Min Act: -0.0000

Data Index: 1130630 (The Pile)

Max Activating Token Index: 250

Text #5

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1315803 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.3678. Min Act: -0.0000

Data Index: 823762 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.3052. Min Act: -0.0000

Data Index: 859387 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1301166 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1850886 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.3110. Min Act: -0.0000

Data Index: 1756237 (The Pile)

Max Activating Token Index: 807

Text #11

Max Range: 1.9968. Min Range: -1.9968

Max Act: 0.9992. Min Act: -0.0000

Data Index: 1316629 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.1745. Min Act: -0.0000

Data Index: 394484 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.1197. Min Act: -0.0000

Data Index: 741898 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.1885. Min Act: -0.0000

Data Index: 1434911 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.3819. Min Act: -0.0000

Data Index: 1787013 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1386289 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.1356. Min Act: -0.0000

Data Index: 1257019 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.1912. Min Act: -0.0000

Data Index: 777692 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 1.9968. Min Range: -1.9968

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1116134 (The Pile)

Max Activating Token Index: 586