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

Dataset: The Pile

Neuron 3723 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: 0.8824. Min Range: -0.8824

Max Act: 0.8824. Min Act: -0.0000

Data Index: 188523 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1283873 (The Pile)

Max Activating Token Index: 909

Text #2

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1952497 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7483. Min Act: -0.0000

Data Index: 204506 (The Pile)

Max Activating Token Index: 89

Text #4

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7347. Min Act: -0.0000

Data Index: 942422 (The Pile)

Max Activating Token Index: 926

Text #5

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7028. Min Act: -0.0000

Data Index: 674493 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1576093 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1055516 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6736. Min Act: -0.0000

Data Index: 805346 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6995. Min Act: -0.0000

Data Index: 836932 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1738943 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6842. Min Act: -0.0000

Data Index: 720789 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1101460 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6629. Min Act: -0.0000

Data Index: 605844 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1034599 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6791. Min Act: -0.0000

Data Index: 186019 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6993. Min Act: -0.0000

Data Index: 424096 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6869. Min Act: -0.0000

Data Index: 502383 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1435897 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6503. Min Act: -0.0000

Data Index: 5195 (The Pile)

Max Activating Token Index: 380