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

Dataset: The Pile

Neuron 1368 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.8810. Min Act: -0.0000

Data Index: 658086 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.7019. Min Act: -0.0000

Data Index: 1760984 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4941. Min Act: -0.0000

Data Index: 48971 (The Pile)

Max Activating Token Index: 984

Text #3

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.6587. Min Act: -0.0000

Data Index: 1149899 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4720. Min Act: -0.0000

Data Index: 1497142 (The Pile)

Max Activating Token Index: 792

Text #5

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.5904. Min Act: -0.0000

Data Index: 72110 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1698306 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4211. Min Act: -0.0000

Data Index: 706385 (The Pile)

Max Activating Token Index: 497

Text #8

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1057070 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.3847. Min Act: -0.0000

Data Index: 897789 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4504. Min Act: -0.0000

Data Index: 895202 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.3501. Min Act: -0.0000

Data Index: 108199 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.4046. Min Act: -0.0000

Data Index: 1311283 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1749686 (The Pile)

Max Activating Token Index: 591

Text #14

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.3194. Min Act: -0.0000

Data Index: 337609 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.2790. Min Act: -0.0000

Data Index: 1992405 (The Pile)

Max Activating Token Index: 362

Text #16

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.3940. Min Act: -0.0000

Data Index: 1457397 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.2790. Min Act: -0.0000

Data Index: 249420 (The Pile)

Max Activating Token Index: 647

Text #18

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.2111. Min Act: -0.0000

Data Index: 91352 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 1.8810. Min Range: -1.8810

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1845022 (The Pile)

Max Activating Token Index: 73