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

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

Neuron 873 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0019. Min Act: -0.0002

Data Index: 827076 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0002

Data Index: 458985 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0002

Data Index: 713543 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0002

Data Index: 168170 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0017. Min Act: -0.0002

Data Index: 1134082 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0002

Data Index: 606979 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0002

Data Index: 776037 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0002

Data Index: 843889 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0016. Min Act: -0.0002

Data Index: 738571 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 920018 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 418495 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 497720 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1277232 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1202359 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1080006 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1020185 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 672950 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 558327 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1212039 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.0019. Min Range: -0.0019

Max Act: 0.0015. Min Act: -0.0002

Data Index: 314498 (C4 (Web Text))

Max Activating Token Index: 778