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

Dataset: The Pile

Neuron 3273 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1847795 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.6177. Min Act: -0.0000

Data Index: 553528 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.6064. Min Act: -0.0000

Data Index: 224553 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5759. Min Act: -0.0000

Data Index: 819500 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5515. Min Act: -0.0000

Data Index: 609308 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1335805 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1693338 (The Pile)

Max Activating Token Index: 24

Text #7

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5611. Min Act: -0.0000

Data Index: 789236 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1844522 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1250341 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5066. Min Act: -0.0000

Data Index: 296644 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4569. Min Act: -0.0000

Data Index: 474024 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4867. Min Act: -0.0000

Data Index: 407073 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1192345 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1204641 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4281. Min Act: -0.0000

Data Index: 541972 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1742749 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1944678 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1937113 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 0.6177. Min Range: -0.6177

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1897204 (The Pile)

Max Activating Token Index: 556