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

Dataset: The Pile

Neuron 97 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: 0.5428. Min Range: -0.5428

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1458740 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1674900 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5300. Min Act: -0.0000

Data Index: 984936 (The Pile)

Max Activating Token Index: 180

Text #3

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4853. Min Act: -0.0000

Data Index: 822173 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1192754 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4148. Min Act: -0.0000

Data Index: 703790 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4087. Min Act: -0.0000

Data Index: 315218 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1358933 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1835621 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3904. Min Act: -0.0000

Data Index: 1342832 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1491595 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3706. Min Act: -0.0000

Data Index: 768950 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1666414 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3813. Min Act: -0.0000

Data Index: 711396 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3802. Min Act: -0.0000

Data Index: 161660 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1600566 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3839. Min Act: -0.0000

Data Index: 352051 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3558. Min Act: -0.0000

Data Index: 324785 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3593. Min Act: -0.0000

Data Index: 199056 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.3982. Min Act: -0.0000

Data Index: 520197 (The Pile)

Max Activating Token Index: 690