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

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

Neuron 1650 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: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0003

Data Index: 1248593 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0002

Data Index: 774909 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 1202136 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0003

Data Index: 245109 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0018. Min Act: -0.0002

Data Index: 760852 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0002

Data Index: 1144510 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 444198 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0003

Data Index: 823151 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 848202 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0002

Data Index: 54944 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 883430 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0003

Data Index: 573210 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0002

Data Index: 1421674 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0003

Data Index: 596262 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0003

Data Index: 802332 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 989436 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0003

Data Index: 767978 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0014. Min Act: -0.0003

Data Index: 126441 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1048161 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1308680 (C4 (Web Text))

Max Activating Token Index: 788