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

Dataset: The Pile

Neuron 2604 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.8683. Min Act: -0.0000

Data Index: 30904 (The Pile)

Max Activating Token Index: 57

Text #1

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1631899 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1729739 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.8210. Min Act: -0.0000

Data Index: 693083 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7736. Min Act: -0.0000

Data Index: 48864 (The Pile)

Max Activating Token Index: 389

Text #5

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1192510 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7485. Min Act: 0.0000

Data Index: 1030375 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1009640 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1381726 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6859. Min Act: -0.0000

Data Index: 321175 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1617811 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1849902 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1087945 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7138. Min Act: -0.0000

Data Index: 568488 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1164761 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6451. Min Act: -0.0000

Data Index: 894597 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6765. Min Act: -0.0000

Data Index: 846823 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6785. Min Act: -0.0000

Data Index: 530132 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.7223. Min Act: -0.0000

Data Index: 396622 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 0.8779. Min Range: -0.8779

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1203561 (The Pile)

Max Activating Token Index: 198