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

Dataset: The Pile

Neuron 1920 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: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0000

Data Index: 1629006 (The Pile)

Max Activating Token Index: 27

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1608461 (The Pile)

Max Activating Token Index: 35

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0000

Data Index: 905591 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1374162 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1248118 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0000

Data Index: 418129 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0000

Data Index: 184817 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0000

Data Index: 845367 (The Pile)

Max Activating Token Index: 48

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 1070264 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0000

Data Index: 1712580 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0000

Data Index: 1225864 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0000

Data Index: 609968 (The Pile)

Max Activating Token Index: 31

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0000

Data Index: 609171 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 788576 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 264184 (The Pile)

Max Activating Token Index: 34

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 160399 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 1849470 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 889219 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0000

Data Index: 1067950 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0000

Data Index: 617294 (The Pile)

Max Activating Token Index: 37