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

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

Neuron 1247 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: 0.1944. Min Range: -0.1944

Max Act: 0.1944. Min Act: -0.0005

Data Index: 470535 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1870. Min Act: -0.0005

Data Index: 598714 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1834. Min Act: -0.0005

Data Index: 987322 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1843. Min Act: -0.0005

Data Index: 139099 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1782. Min Act: -0.0005

Data Index: 50311 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1753. Min Act: -0.0005

Data Index: 814652 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1737. Min Act: -0.0005

Data Index: 927403 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1700. Min Act: -0.0005

Data Index: 457684 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1679. Min Act: -0.0005

Data Index: 356935 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1806. Min Act: -0.0005

Data Index: 1070388 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1715. Min Act: -0.0005

Data Index: 111335 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1708. Min Act: -0.0005

Data Index: 333865 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1787. Min Act: -0.0005

Data Index: 1341354 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1648. Min Act: -0.0005

Data Index: 135736 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1771. Min Act: -0.0005

Data Index: 223407 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1667. Min Act: -0.0005

Data Index: 592334 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1696. Min Act: -0.0005

Data Index: 805362 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1615. Min Act: -0.0005

Data Index: 806616 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1682. Min Act: -0.0005

Data Index: 475250 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.1944. Min Range: -0.1944

Max Act: 0.1728. Min Act: -0.0005

Data Index: 363041 (C4 (Web Text))

Max Activating Token Index: 639