Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 506 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0082. Min Act: -0.0005

Data Index: 716038 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0080. Min Act: -0.0006

Data Index: 521613 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1269819 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0079. Min Act: -0.0006

Data Index: 327535 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0079. Min Act: -0.0006

Data Index: 450042 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0075. Min Act: -0.0006

Data Index: 21003 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1317668 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1524581 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1445121 (Python Code)

Max Activating Token Index: 992

Text #9

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0074. Min Act: -0.0006

Data Index: 821189 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0075. Min Act: -0.0006

Data Index: 686946 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1192742 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1035876 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0076. Min Act: -0.0006

Data Index: 887779 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1087032 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1510934 (Python Code)

Max Activating Token Index: 1015

Text #16

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0072. Min Act: -0.0006

Data Index: 303930 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0073. Min Act: -0.0006

Data Index: 631471 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0073. Min Act: -0.0006

Data Index: 798763 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0082. Min Range: -0.0082

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1322484 (C4 (Web Text))

Max Activating Token Index: 154