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

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

Neuron 2529 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0001

Data Index: 614514 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0828. Min Act: -0.0002

Data Index: 779416 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0770. Min Act: -0.0001

Data Index: 893568 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0711. Min Act: -0.0001

Data Index: 760148 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1211865 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0719. Min Act: -0.0002

Data Index: 261423 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1014896 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0749. Min Act: -0.0001

Data Index: 833822 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1149649 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0758. Min Act: -0.0001

Data Index: 472542 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1081896 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0708. Min Act: -0.0001

Data Index: 348478 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1018003 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0740. Min Act: -0.0001

Data Index: 150177 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0708. Min Act: -0.0001

Data Index: 525722 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0640. Min Act: -0.0001

Data Index: 588875 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0666. Min Act: -0.0002

Data Index: 20927 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0675. Min Act: -0.0002

Data Index: 493766 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0707. Min Act: -0.0001

Data Index: 326967 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0662. Min Act: -0.0001

Data Index: 548749 (C4 (Web Text))

Max Activating Token Index: 802