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

Dataset: The Pile

Neuron 664 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7960. Min Act: -0.0000

Data Index: 437301 (The Pile)

Max Activating Token Index: 841

Text #1

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1640848 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8509. Min Act: -0.0000

Data Index: 336947 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8101. Min Act: -0.0000

Data Index: 980069 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7301. Min Act: -0.0000

Data Index: 739965 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7290. Min Act: -0.0000

Data Index: 317259 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1875291 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7120. Min Act: -0.0000

Data Index: 512813 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7493. Min Act: -0.0000

Data Index: 197227 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7058. Min Act: -0.0000

Data Index: 741559 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.6956. Min Act: -0.0000

Data Index: 210438 (The Pile)

Max Activating Token Index: 475

Text #11

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.6731. Min Act: -0.0000

Data Index: 802147 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7105. Min Act: -0.0000

Data Index: 76805 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7269. Min Act: -0.0000

Data Index: 16467 (The Pile)

Max Activating Token Index: 761

Text #14

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7254. Min Act: -0.0000

Data Index: 422743 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7681. Min Act: -0.0000

Data Index: 131838 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1503793 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.8007. Min Act: -0.0000

Data Index: 1599332 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1212620 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.8509. Min Range: -0.8509

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1601119 (The Pile)

Max Activating Token Index: 583