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

Dataset: The Pile

Neuron 934 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6255. Min Act: -0.0000

Data Index: 822027 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5639. Min Act: -0.0000

Data Index: 607721 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5590. Min Act: -0.0000

Data Index: 722514 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1995155 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1960815 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1751489 (The Pile)

Max Activating Token Index: 272

Text #6

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4761. Min Act: -0.0000

Data Index: 655812 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1697156 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1311196 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1406196 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1485504 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4633. Min Act: -0.0000

Data Index: 319999 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4525. Min Act: -0.0000

Data Index: 118388 (The Pile)

Max Activating Token Index: 488

Text #13

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4907. Min Act: -0.0000

Data Index: 824300 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4778. Min Act: -0.0000

Data Index: 176372 (The Pile)

Max Activating Token Index: 845

Text #15

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4651. Min Act: -0.0000

Data Index: 637375 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1042931 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4424. Min Act: -0.0000

Data Index: 844985 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1289755 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4388. Min Act: -0.0000

Data Index: 1140135 (The Pile)

Max Activating Token Index: 495