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

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

Neuron 1479 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: 0.0025. Min Range: -0.0025

Max Act: 0.0025. Min Act: -0.0003

Data Index: 375083 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0019. Min Act: -0.0004

Data Index: 124980 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0019. Min Act: -0.0004

Data Index: 1191122 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0018. Min Act: -0.0004

Data Index: 10862 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0017. Min Act: -0.0003

Data Index: 234317 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0018. Min Act: -0.0003

Data Index: 720055 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0017. Min Act: -0.0004

Data Index: 1267648 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0017. Min Act: -0.0003

Data Index: 592960 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0017. Min Act: -0.0003

Data Index: 1081043 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0017. Min Act: -0.0004

Data Index: 127447 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0017. Min Act: -0.0004

Data Index: 1066944 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0016. Min Act: -0.0004

Data Index: 967232 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0016. Min Act: -0.0004

Data Index: 16629 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0016. Min Act: -0.0003

Data Index: 1635084 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1385689 (Python Code)

Max Activating Token Index: 655

Text #15

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0015. Min Act: -0.0003

Data Index: 343270 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0015. Min Act: -0.0003

Data Index: 1505339 (Python Code)

Max Activating Token Index: 582

Text #17

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0014. Min Act: -0.0003

Data Index: 723035 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0015. Min Act: -0.0003

Data Index: 215569 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0025. Min Range: -0.0025

Max Act: 0.0015. Min Act: -0.0004

Data Index: 941271 (C4 (Web Text))

Max Activating Token Index: 488