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

Dataset: The Pile

Neuron 2508 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: 0.9459. Min Range: -0.9459

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1511298 (The Pile)

Max Activating Token Index: 787

Text #1

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.9001. Min Act: -0.0000

Data Index: 587411 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1155742 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8760. Min Act: -0.0000

Data Index: 17068 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1157336 (The Pile)

Max Activating Token Index: 714

Text #5

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1597121 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1189748 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1225024 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8148. Min Act: -0.0000

Data Index: 990070 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1425880 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7151. Min Act: -0.0000

Data Index: 511267 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7621. Min Act: -0.0000

Data Index: 883106 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1973721 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1059765 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7461. Min Act: -0.0000

Data Index: 504124 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1211752 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1588701 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1823837 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1696347 (The Pile)

Max Activating Token Index: 525

Text #19

Max Range: 0.9459. Min Range: -0.9459

Max Act: 0.7664. Min Act: -0.0000

Data Index: 517742 (The Pile)

Max Activating Token Index: 82