Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 716 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0681. Min Act: -0.0005

Data Index: 1614264 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0665. Min Act: -0.0005

Data Index: 1534382 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0005

Data Index: 1361760 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0635. Min Act: -0.0005

Data Index: 1561259 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0636. Min Act: -0.0005

Data Index: 1505090 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0609. Min Act: -0.0005

Data Index: 562431 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0630. Min Act: -0.0005

Data Index: 1445024 (Python Code)

Max Activating Token Index: 565

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0629. Min Act: -0.0005

Data Index: 1249315 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0639. Min Act: -0.0005

Data Index: 1521932 (Python Code)

Max Activating Token Index: 894

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0628. Min Act: -0.0005

Data Index: 108801 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0627. Min Act: -0.0005

Data Index: 1504982 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0570. Min Act: -0.0005

Data Index: 508773 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0597. Min Act: -0.0005

Data Index: 533387 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0593. Min Act: -0.0005

Data Index: 284240 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0597. Min Act: -0.0005

Data Index: 87289 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0568. Min Act: -0.0005

Data Index: 708600 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0580. Min Act: -0.0005

Data Index: 1207894 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0572. Min Act: -0.0005

Data Index: 1598480 (Python Code)

Max Activating Token Index: 1009

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0569. Min Act: -0.0005

Data Index: 976155 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0585. Min Act: -0.0005

Data Index: 880760 (C4 (Web Text))

Max Activating Token Index: 363