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

Dataset: The Pile

Neuron 3206 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: 0.0870. Min Range: -0.0870

Max Act: 0.0870. Min Act: -0.0000

Data Index: 230074 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0770. Min Act: -0.0000

Data Index: 927899 (The Pile)

Max Activating Token Index: 841

Text #2

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0704. Min Act: -0.0000

Data Index: 992454 (The Pile)

Max Activating Token Index: 252

Text #3

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0796. Min Act: -0.0000

Data Index: 527609 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0706. Min Act: -0.0000

Data Index: 103649 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1549894 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1234349 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0695. Min Act: -0.0000

Data Index: 825028 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0675. Min Act: 0.0000

Data Index: 1464483 (The Pile)

Max Activating Token Index: 1017

Text #9

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1449883 (The Pile)

Max Activating Token Index: 953

Text #10

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1186082 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0618. Min Act: -0.0000

Data Index: 350286 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1346923 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0655. Min Act: 0.0000

Data Index: 1216742 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0644. Min Act: -0.0000

Data Index: 882249 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0651. Min Act: -0.0000

Data Index: 401825 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1779003 (The Pile)

Max Activating Token Index: 17

Text #17

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1372668 (The Pile)

Max Activating Token Index: 305

Text #18

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1109220 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.0870. Min Range: -0.0870

Max Act: 0.0601. Min Act: -0.0000

Data Index: 266278 (The Pile)

Max Activating Token Index: 293