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

Dataset: The Pile

Neuron 628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0079. Min Range: -1.0079

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1216716 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9794. Min Act: -0.0000

Data Index: 899007 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9271. Min Act: -0.0000

Data Index: 105660 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8787. Min Act: -0.0000

Data Index: 999401 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9582. Min Act: -0.0000

Data Index: 201262 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1655960 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8812. Min Act: -0.0000

Data Index: 772520 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1620664 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8527. Min Act: -0.0000

Data Index: 913545 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1009011 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1490002 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8297. Min Act: -0.0000

Data Index: 918255 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8392. Min Act: -0.0000

Data Index: 1056179 (The Pile)

Max Activating Token Index: 103

Text #13

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1863737 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7476. Min Act: -0.0000

Data Index: 324785 (The Pile)

Max Activating Token Index: 75

Text #15

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1415829 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1648741 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8181. Min Act: -0.0000

Data Index: 354179 (The Pile)

Max Activating Token Index: 867

Text #18

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1527975 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1944175 (The Pile)

Max Activating Token Index: 553