Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3114 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1510891 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1462997 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1465843 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1559097 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1479713 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1566359 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1651785 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1420305 (Python Code)

Max Activating Token Index: 309

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1360320 (Python Code)

Max Activating Token Index: 524

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1506393 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1614074 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1501791 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1469451 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1583504 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1448778 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1508192 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1571305 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1585964 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1461176 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1430338 (Python Code)

Max Activating Token Index: 731