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

Dataset: The Pile

Neuron 1803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.8156. Min Act: -0.0000

Data Index: 1755048 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.9772. Min Act: -0.0000

Data Index: 1786001 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.7512. Min Act: -0.0000

Data Index: 1018629 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1322792 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.8520. Min Act: -0.0000

Data Index: 1221053 (The Pile)

Max Activating Token Index: 315

Text #5

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.7025. Min Act: -0.0000

Data Index: 1789241 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.6785. Min Act: -0.0000

Data Index: 914746 (The Pile)

Max Activating Token Index: 760

Text #7

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1359127 (The Pile)

Max Activating Token Index: 771

Text #8

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.5350. Min Act: -0.0000

Data Index: 1398411 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.6397. Min Act: -0.0000

Data Index: 720824 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.5245. Min Act: -0.0000

Data Index: 689160 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.5874. Min Act: -0.0000

Data Index: 729897 (The Pile)

Max Activating Token Index: 506

Text #12

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.5701. Min Act: -0.0000

Data Index: 1930377 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.7413. Min Act: -0.0000

Data Index: 561873 (The Pile)

Max Activating Token Index: 651

Text #14

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1962577 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.3964. Min Act: -0.0000

Data Index: 79299 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.4869. Min Act: -0.0000

Data Index: 93792 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.5615. Min Act: -0.0000

Data Index: 204506 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.4722. Min Act: -0.0000

Data Index: 1889477 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 1.9772. Min Range: -1.9772

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1278527 (The Pile)

Max Activating Token Index: 566