Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1443 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1197. Min Act: -0.0001

Data Index: 129148 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1093. Min Act: -0.0001

Data Index: 665721 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.1064. Min Act: -0.0001

Data Index: 674407 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0761. Min Act: -0.0001

Data Index: 357324 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0704. Min Act: -0.0001

Data Index: 748242 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1632720 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1359342 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1405069 (Python Code)

Max Activating Token Index: 340

Text #8

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0822. Min Act: -0.0001

Data Index: 584562 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1570799 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0674. Min Act: -0.0001

Data Index: 755217 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0684. Min Act: -0.0001

Data Index: 445951 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1166273 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1195847 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0690. Min Act: -0.0001

Data Index: 129629 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1047778 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1189944 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0673. Min Act: -0.0001

Data Index: 125408 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1148002 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.1197. Min Range: -0.1197

Max Act: 0.0572. Min Act: -0.0001

Data Index: 253555 (C4 (Web Text))

Max Activating Token Index: 308