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

Dataset: The Pile

Neuron 1511 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.1109. Min Act: 0.0000

Data Index: 1621305 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0581. Min Act: 0.0000

Data Index: 535394 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0421. Min Act: 0.0000

Data Index: 740692 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 1.1109. Min Range: -1.1109

Max Act: 1.0079. Min Act: 0.0000

Data Index: 669759 (The Pile)

Max Activating Token Index: 726

Text #4

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9908. Min Act: 0.0000

Data Index: 1616250 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9424. Min Act: 0.0000

Data Index: 874793 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8800. Min Act: 0.0000

Data Index: 1465202 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.9102. Min Act: 0.0000

Data Index: 617343 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8719. Min Act: 0.0000

Data Index: 961785 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8062. Min Act: 0.0000

Data Index: 1291723 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8459. Min Act: 0.0000

Data Index: 1469750 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8979. Min Act: 0.0000

Data Index: 839849 (The Pile)

Max Activating Token Index: 57

Text #12

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8738. Min Act: 0.0000

Data Index: 1333506 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8175. Min Act: 0.0000

Data Index: 1111758 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8013. Min Act: 0.0000

Data Index: 764109 (The Pile)

Max Activating Token Index: 80

Text #15

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8056. Min Act: 0.0000

Data Index: 1337215 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8050. Min Act: 0.0000

Data Index: 1674517 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8536. Min Act: 0.0000

Data Index: 1163313 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.8019. Min Act: 0.0000

Data Index: 580989 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.1109. Min Range: -1.1109

Max Act: 0.7958. Min Act: -0.0000

Data Index: 564267 (The Pile)

Max Activating Token Index: 583