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

Dataset: The Pile

Neuron 4375 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0011. Min Act: -0.0000

Data Index: 1800582 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0011. Min Act: -0.0000

Data Index: 1811908 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0011. Min Act: -0.0000

Data Index: 1477023 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0011. Min Act: -0.0000

Data Index: 132039 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 909565 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 721766 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1226206 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1756026 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1536848 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1367622 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1647784 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 676437 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1640570 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 150028 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1532373 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 659706 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1840204 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 567993 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1141622 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0011. Min Range: -0.0011

Max Act: 0.0010. Min Act: -0.0000

Data Index: 106734 (The Pile)

Max Activating Token Index: 1023