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

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

Neuron 870 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: 0.0847. Min Range: -0.0847

Max Act: 0.0847. Min Act: -0.0005

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0826. Min Act: -0.0005

Data Index: 870026 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0678. Min Act: -0.0005

Data Index: 733665 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0685. Min Act: -0.0005

Data Index: 277937 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0691. Min Act: -0.0005

Data Index: 779926 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0671. Min Act: -0.0005

Data Index: 906006 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0670. Min Act: -0.0004

Data Index: 167998 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0666. Min Act: -0.0005

Data Index: 953664 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0664. Min Act: -0.0005

Data Index: 1298380 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0657. Min Act: -0.0005

Data Index: 523504 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0647. Min Act: -0.0005

Data Index: 418560 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0668. Min Act: -0.0005

Data Index: 784372 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0630. Min Act: -0.0005

Data Index: 981654 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0636. Min Act: -0.0005

Data Index: 150393 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0618. Min Act: -0.0005

Data Index: 231319 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0599. Min Act: -0.0005

Data Index: 470020 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0642. Min Act: -0.0005

Data Index: 1244166 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0587. Min Act: -0.0005

Data Index: 712994 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0588. Min Act: -0.0005

Data Index: 709542 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0608. Min Act: -0.0005

Data Index: 1301350 (C4 (Web Text))

Max Activating Token Index: 393