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

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

Neuron 1779 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.1401. Min Act: -0.0001

Data Index: 1133263 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9779. Min Act: -0.0001

Data Index: 1245638 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8819. Min Act: -0.0001

Data Index: 100737 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9009. Min Act: -0.0001

Data Index: 743700 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 1.1401. Min Range: -1.1401

Max Act: 1.0204. Min Act: -0.0001

Data Index: 1037474 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9891. Min Act: -0.0001

Data Index: 1027833 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9991. Min Act: -0.0001

Data Index: 758522 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8955. Min Act: -0.0001

Data Index: 767642 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8978. Min Act: -0.0001

Data Index: 488859 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9503. Min Act: -0.0001

Data Index: 1306378 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9736. Min Act: -0.0001

Data Index: 660441 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8948. Min Act: -0.0001

Data Index: 1298356 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9264. Min Act: -0.0001

Data Index: 212968 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.9138. Min Act: -0.0001

Data Index: 164930 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8828. Min Act: -0.0001

Data Index: 797946 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8794. Min Act: -0.0001

Data Index: 872171 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8762. Min Act: -0.0001

Data Index: 1192025 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8499. Min Act: -0.0001

Data Index: 869263 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8607. Min Act: -0.0001

Data Index: 647875 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.1401. Min Range: -1.1401

Max Act: 0.8384. Min Act: -0.0001

Data Index: 284390 (C4 (Web Text))

Max Activating Token Index: 986