Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 230 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0021. Min Act: -0.0003

Data Index: 1481860 (Python Code)

Max Activating Token Index: 740

Text #1

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0021. Min Act: -0.0003

Data Index: 1491004 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0020. Min Act: -0.0003

Data Index: 1503275 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0020. Min Act: -0.0003

Data Index: 559511 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0003

Data Index: 298252 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0004

Data Index: 525403 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0004

Data Index: 1071610 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0004

Data Index: 172512 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1565536 (Python Code)

Max Activating Token Index: 929

Text #9

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0004

Data Index: 870591 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1437299 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0004

Data Index: 20016 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1374389 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0004

Data Index: 277345 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1289071 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0003

Data Index: 14165 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0004

Data Index: 897965 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0004

Data Index: 342437 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0004

Data Index: 672669 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0004

Data Index: 529095 (C4 (Web Text))

Max Activating Token Index: 862