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

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

Neuron 2927 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1412. Min Act: -0.0002

Data Index: 1258474 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1114. Min Act: -0.0002

Data Index: 96392 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1065. Min Act: -0.0002

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1391547 (Python Code)

Max Activating Token Index: 622

Text #4

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1426509 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0999. Min Act: -0.0002

Data Index: 373660 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1055. Min Act: -0.0002

Data Index: 1556849 (Python Code)

Max Activating Token Index: 763

Text #7

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1644487 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1191. Min Act: -0.0002

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1530095 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0902. Min Act: -0.0002

Data Index: 801649 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1490612 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1651461 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1561557 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1554591 (Python Code)

Max Activating Token Index: 80

Text #15

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1619752 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1592840 (Python Code)

Max Activating Token Index: 426

Text #17

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.1012. Min Act: -0.0002

Data Index: 618269 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0869. Min Act: -0.0002

Data Index: 1481338 (Python Code)

Max Activating Token Index: 855

Text #19

Max Range: 0.1412. Min Range: -0.1412

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1537358 (Python Code)

Max Activating Token Index: 696