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

Dataset: The Pile

Neuron 1082 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: 0.8611. Min Range: -0.8611

Max Act: 0.8611. Min Act: -0.0000

Data Index: 934690 (The Pile)

Max Activating Token Index: 819

Text #1

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7886. Min Act: -0.0000

Data Index: 710838 (The Pile)

Max Activating Token Index: 741

Text #2

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1226684 (The Pile)

Max Activating Token Index: 680

Text #3

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6974. Min Act: -0.0000

Data Index: 180883 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6793. Min Act: -0.0000

Data Index: 801221 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1979767 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1730585 (The Pile)

Max Activating Token Index: 952

Text #7

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6463. Min Act: -0.0000

Data Index: 344984 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1936975 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1648121 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6470. Min Act: -0.0000

Data Index: 666385 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5628. Min Act: -0.0000

Data Index: 145436 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1030876 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5075. Min Act: -0.0000

Data Index: 851154 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1647605 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1438490 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1445983 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.5639. Min Act: -0.0000

Data Index: 780615 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.6035. Min Act: -0.0000

Data Index: 963539 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 0.8611. Min Range: -0.8611

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1278690 (The Pile)

Max Activating Token Index: 614