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

Dataset: The Pile

Neuron 2398 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: 1.7083. Min Range: -1.7083

Max Act: 1.7083. Min Act: -0.0000

Data Index: 643438 (The Pile)

Max Activating Token Index: 885

Text #1

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6817. Min Act: -0.0000

Data Index: 577916 (The Pile)

Max Activating Token Index: 554

Text #2

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6071. Min Act: -0.0000

Data Index: 513004 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5798. Min Act: -0.0000

Data Index: 672257 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5613. Min Act: -0.0000

Data Index: 799247 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5675. Min Act: -0.0000

Data Index: 1884132 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5264. Min Act: -0.0000

Data Index: 72170 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5422. Min Act: -0.0000

Data Index: 574736 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.6025. Min Act: -0.0000

Data Index: 511823 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5094. Min Act: -0.0000

Data Index: 805055 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.4861. Min Act: -0.0000

Data Index: 457382 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.3822. Min Act: -0.0000

Data Index: 903558 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.4941. Min Act: -0.0000

Data Index: 707162 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1821795 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.4968. Min Act: -0.0000

Data Index: 566628 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1747468 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.3072. Min Act: -0.0000

Data Index: 168587 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.4574. Min Act: -0.0000

Data Index: 673369 (The Pile)

Max Activating Token Index: 292

Text #18

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.3668. Min Act: -0.0000

Data Index: 945028 (The Pile)

Max Activating Token Index: 708

Text #19

Max Range: 1.7083. Min Range: -1.7083

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1534050 (The Pile)

Max Activating Token Index: 1006