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

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

Neuron 3554 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1650629 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0021. Min Act: -0.0002

Data Index: 1229634 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0020. Min Act: -0.0002

Data Index: 194035 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 1382492 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0019. Min Act: -0.0002

Data Index: 1610261 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 937303 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 1401258 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0002

Data Index: 1498044 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0018. Min Act: -0.0002

Data Index: 1405796 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0017. Min Act: -0.0002

Data Index: 1523385 (Python Code)

Max Activating Token Index: 162

Text #10

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0016. Min Act: -0.0002

Data Index: 446755 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0016. Min Act: -0.0002

Data Index: 1047004 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0016. Min Act: -0.0002

Data Index: 630909 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0016. Min Act: -0.0002

Data Index: 23142 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0016. Min Act: -0.0002

Data Index: 1415062 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0015. Min Act: -0.0002

Data Index: 566669 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0016. Min Act: -0.0002

Data Index: 77920 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0015. Min Act: -0.0002

Data Index: 94137 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0015. Min Act: -0.0002

Data Index: 287631 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.0021. Min Range: -0.0021

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1250949 (C4 (Web Text))

Max Activating Token Index: 183