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

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

Neuron 1464 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.1082. Min Act: -0.0003

Data Index: 1127308 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0989. Min Act: -0.0004

Data Index: 255892 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0976. Min Act: -0.0003

Data Index: 1181731 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0949. Min Act: -0.0004

Data Index: 1254725 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0913. Min Act: -0.0004

Data Index: 791162 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0848. Min Act: -0.0003

Data Index: 974831 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1213695 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0846. Min Act: -0.0004

Data Index: 623245 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0847. Min Act: -0.0003

Data Index: 1230297 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0848. Min Act: -0.0003

Data Index: 213397 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0855. Min Act: -0.0003

Data Index: 320794 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0820. Min Act: -0.0003

Data Index: 978516 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0821. Min Act: -0.0003

Data Index: 589308 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0800. Min Act: -0.0003

Data Index: 767343 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0813. Min Act: -0.0003

Data Index: 711773 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0794. Min Act: -0.0003

Data Index: 271661 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0795. Min Act: -0.0003

Data Index: 1233741 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0797. Min Act: -0.0003

Data Index: 437476 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0786. Min Act: -0.0003

Data Index: 301214 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.1082. Min Range: -0.1082

Max Act: 0.0800. Min Act: -0.0003

Data Index: 995669 (C4 (Web Text))

Max Activating Token Index: 78