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

Dataset: The Pile

Neuron 3596 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: 5.4642. Min Range: -5.4642

Max Act: 5.4642. Min Act: -0.0000

Data Index: 341722 (The Pile)

Max Activating Token Index: 885

Text #1

Max Range: 5.4642. Min Range: -5.4642

Max Act: 4.2300. Min Act: -0.0000

Data Index: 909234 (The Pile)

Max Activating Token Index: 321

Text #2

Max Range: 5.4642. Min Range: -5.4642

Max Act: 4.2305. Min Act: -0.0000

Data Index: 1040535 (The Pile)

Max Activating Token Index: 614

Text #3

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.8308. Min Act: -0.0000

Data Index: 927865 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.3677. Min Act: 0.0000

Data Index: 516179 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.6696. Min Act: -0.0000

Data Index: 298941 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.8281. Min Act: -0.0000

Data Index: 865055 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.4059. Min Act: 0.0000

Data Index: 1219107 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.4737. Min Act: -0.0000

Data Index: 1633726 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.1613. Min Act: -0.0000

Data Index: 1035038 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.0398. Min Act: -0.0000

Data Index: 1359698 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 5.4642. Min Range: -5.4642

Max Act: 2.9470. Min Act: -0.0000

Data Index: 278569 (The Pile)

Max Activating Token Index: 978

Text #12

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.2103. Min Act: -0.0000

Data Index: 794137 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.0239. Min Act: -0.0000

Data Index: 1487039 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 5.4642. Min Range: -5.4642

Max Act: 2.9857. Min Act: 0.0000

Data Index: 844341 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 5.4642. Min Range: -5.4642

Max Act: 3.2837. Min Act: -0.0000

Data Index: 1368245 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 5.4642. Min Range: -5.4642

Max Act: 2.9029. Min Act: -0.0000

Data Index: 222989 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 5.4642. Min Range: -5.4642

Max Act: 2.8008. Min Act: -0.0000

Data Index: 825790 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 5.4642. Min Range: -5.4642

Max Act: 2.6860. Min Act: -0.0000

Data Index: 74769 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 5.4642. Min Range: -5.4642

Max Act: 2.8990. Min Act: -0.0000

Data Index: 1767863 (The Pile)

Max Activating Token Index: 103