Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3535 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0000

Data Index: 1838356 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0000

Data Index: 846948 (The Pile)

Max Activating Token Index: 1022

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0000

Data Index: 259713 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0000

Data Index: 297203 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1010127 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0000

Data Index: 423336 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0001

Data Index: 1669768 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0000

Data Index: 804079 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0000

Data Index: 1014944 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0000

Data Index: 1329388 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0000

Data Index: 1128276 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0000

Data Index: 600609 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0000

Data Index: 59075 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0001

Data Index: 1553570 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 1173672 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0000

Data Index: 1805007 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0001

Data Index: 1898872 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0000

Data Index: 1383934 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0000

Data Index: 150086 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0076. Min Act: -0.0001

Data Index: 865139 (The Pile)

Max Activating Token Index: 1023