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

Dataset: The Pile

Neuron 4188 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7358. Min Act: -0.0000

Data Index: 203667 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1094184 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7419. Min Act: -0.0000

Data Index: 168223 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1105416 (The Pile)

Max Activating Token Index: 975

Text #4

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6865. Min Act: -0.0000

Data Index: 199614 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6926. Min Act: -0.0000

Data Index: 196094 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1129802 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1931767 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5798. Min Act: -0.0000

Data Index: 122662 (The Pile)

Max Activating Token Index: 970

Text #9

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1672542 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1433251 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5676. Min Act: -0.0000

Data Index: 578544 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1892439 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1450217 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5550. Min Act: -0.0000

Data Index: 612564 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5868. Min Act: -0.0000

Data Index: 454146 (The Pile)

Max Activating Token Index: 310

Text #16

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5445. Min Act: -0.0000

Data Index: 494323 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1399521 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.5285. Min Act: -0.0000

Data Index: 1785459 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.4802. Min Act: -0.0000

Data Index: 480152 (The Pile)

Max Activating Token Index: 676