Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5054 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1570713 (Python Code)

Max Activating Token Index: 942

Text #1

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0698. Min Act: -0.0002

Data Index: 978560 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0646. Min Act: -0.0002

Data Index: 916878 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1486255 (Python Code)

Max Activating Token Index: 408

Text #4

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0649. Min Act: -0.0003

Data Index: 651024 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0671. Min Act: -0.0003

Data Index: 813770 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0659. Min Act: -0.0002

Data Index: 372424 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1440416 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1180350 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0652. Min Act: -0.0002

Data Index: 816776 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1076067 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0647. Min Act: -0.0002

Data Index: 986690 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0656. Min Act: -0.0003

Data Index: 985020 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0668. Min Act: -0.0003

Data Index: 1482466 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0644. Min Act: -0.0002

Data Index: 587334 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1293091 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0661. Min Act: -0.0002

Data Index: 425029 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0645. Min Act: -0.0002

Data Index: 332593 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1501801 (Python Code)

Max Activating Token Index: 261

Text #19

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0605. Min Act: -0.0003

Data Index: 908107 (C4 (Web Text))

Max Activating Token Index: 443