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

Dataset: The Pile

Neuron 3731 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: 0.8903. Min Range: -0.8903

Max Act: 0.8903. Min Act: -0.0000

Data Index: 648746 (The Pile)

Max Activating Token Index: 664

Text #1

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7940. Min Act: -0.0000

Data Index: 13512 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6876. Min Act: -0.0000

Data Index: 167393 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1646071 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6855. Min Act: -0.0000

Data Index: 287031 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1891212 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6445. Min Act: -0.0000

Data Index: 774044 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1318283 (The Pile)

Max Activating Token Index: 172

Text #8

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6576. Min Act: -0.0000

Data Index: 851530 (The Pile)

Max Activating Token Index: 839

Text #9

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6409. Min Act: -0.0000

Data Index: 645860 (The Pile)

Max Activating Token Index: 159

Text #10

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1158866 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1033888 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6646. Min Act: -0.0000

Data Index: 56027 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1107822 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.5951. Min Act: -0.0000

Data Index: 231154 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1773617 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6140. Min Act: -0.0000

Data Index: 925439 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6743. Min Act: -0.0000

Data Index: 139391 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6377. Min Act: -0.0000

Data Index: 136278 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 0.8903. Min Range: -0.8903

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1516103 (The Pile)

Max Activating Token Index: 572