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

Dataset: The Pile

Neuron 2473 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: 1.3030. Min Range: -1.3030

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1874039 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 1.3030. Min Range: -1.3030

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1514048 (The Pile)

Max Activating Token Index: 77

Text #2

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.9375. Min Act: -0.0000

Data Index: 549779 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8574. Min Act: -0.0000

Data Index: 164878 (The Pile)

Max Activating Token Index: 840

Text #4

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.8672. Min Act: -0.0000

Data Index: 738683 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.7494. Min Act: -0.0000

Data Index: 810805 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.7746. Min Act: -0.0000

Data Index: 378345 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.7428. Min Act: -0.0000

Data Index: 1010671 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1520374 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1578248 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1445860 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1263275 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.7321. Min Act: -0.0000

Data Index: 286131 (The Pile)

Max Activating Token Index: 494

Text #13

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1374883 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1841420 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6653. Min Act: -0.0000

Data Index: 241783 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6591. Min Act: -0.0000

Data Index: 92898 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6550. Min Act: -0.0000

Data Index: 424644 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1585093 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 1.3030. Min Range: -1.3030

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1269460 (The Pile)

Max Activating Token Index: 910