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

Dataset: The Pile

Neuron 4447 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: 5.6209. Min Range: -5.6209

Max Act: 5.6209. Min Act: -0.0000

Data Index: 1428541 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.2427. Min Act: -0.0000

Data Index: 767722 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.2085. Min Act: -0.0000

Data Index: 649062 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.0404. Min Act: -0.0000

Data Index: 1780765 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.5921. Min Act: -0.0000

Data Index: 1985907 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.8695. Min Act: -0.0000

Data Index: 1127831 (The Pile)

Max Activating Token Index: 493

Text #6

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.3375. Min Act: -0.0000

Data Index: 1061612 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.6620. Min Act: -0.0000

Data Index: 65666 (The Pile)

Max Activating Token Index: 692

Text #8

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.6106. Min Act: -0.0000

Data Index: 950607 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.7033. Min Act: -0.0000

Data Index: 146832 (The Pile)

Max Activating Token Index: 654

Text #10

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.6921. Min Act: -0.0000

Data Index: 1449030 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.5335. Min Act: -0.0000

Data Index: 1639788 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.6523. Min Act: -0.0000

Data Index: 1239873 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.4780. Min Act: -0.0000

Data Index: 1355358 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.7944. Min Act: -0.0000

Data Index: 1105573 (The Pile)

Max Activating Token Index: 979

Text #15

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.5604. Min Act: -0.0000

Data Index: 991977 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.2763. Min Act: -0.0000

Data Index: 518020 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.5848. Min Act: -0.0000

Data Index: 1439956 (The Pile)

Max Activating Token Index: 344

Text #18

Max Range: 5.6209. Min Range: -5.6209

Max Act: 4.5929. Min Act: -0.0000

Data Index: 210847 (The Pile)

Max Activating Token Index: 392

Text #19

Max Range: 5.6209. Min Range: -5.6209

Max Act: 3.8836. Min Act: -0.0000

Data Index: 565104 (The Pile)

Max Activating Token Index: 791