Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1965 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7327. Min Act: -0.0004

Data Index: 861751 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7030. Min Act: -0.0004

Data Index: 529752 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6612. Min Act: -0.0004

Data Index: 739721 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7061. Min Act: -0.0004

Data Index: 1302188 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6805. Min Act: -0.0004

Data Index: 1122563 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6784. Min Act: -0.0004

Data Index: 1058991 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6782. Min Act: -0.0004

Data Index: 750391 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6898. Min Act: -0.0004

Data Index: 1000632 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6216. Min Act: -0.0004

Data Index: 376780 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6871. Min Act: -0.0004

Data Index: 1286380 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7029. Min Act: -0.0004

Data Index: 1037083 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.5595. Min Act: -0.0004

Data Index: 574822 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6557. Min Act: -0.0004

Data Index: 259314 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.7665. Min Act: -0.0004

Data Index: 143142 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6746. Min Act: -0.0004

Data Index: 1271011 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6953. Min Act: -0.0004

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6068. Min Act: -0.0004

Data Index: 1332133 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6865. Min Act: -0.0004

Data Index: 179863 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6405. Min Act: -0.0004

Data Index: 1191629 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.7665. Min Range: -0.7665

Max Act: 0.6410. Min Act: -0.0004

Data Index: 1112414 (C4 (Web Text))

Max Activating Token Index: 820