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

Dataset: The Pile

Neuron 2551 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: 0.8049. Min Range: -0.8049

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1973533 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7810. Min Act: -0.0000

Data Index: 261396 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1396437 (The Pile)

Max Activating Token Index: 975

Text #3

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7628. Min Act: 0.0000

Data Index: 926181 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6683. Min Act: -0.0000

Data Index: 163571 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7596. Min Act: -0.0000

Data Index: 266355 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6427. Min Act: 0.0000

Data Index: 1228146 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.7024. Min Act: -0.0000

Data Index: 201784 (The Pile)

Max Activating Token Index: 982

Text #8

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5773. Min Act: -0.0000

Data Index: 137293 (The Pile)

Max Activating Token Index: 908

Text #9

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1347012 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6132. Min Act: -0.0000

Data Index: 664147 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5326. Min Act: -0.0000

Data Index: 855058 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1350959 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5476. Min Act: -0.0000

Data Index: 809177 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1482762 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5558. Min Act: -0.0000

Data Index: 833238 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1488389 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5492. Min Act: -0.0000

Data Index: 675865 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1886192 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 0.8049. Min Range: -0.8049

Max Act: 0.5373. Min Act: 0.0000

Data Index: 136091 (The Pile)

Max Activating Token Index: 837