Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1264 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0005

Data Index: 1127520 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0799. Min Act: -0.0006

Data Index: 825253 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0765. Min Act: -0.0006

Data Index: 740267 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0758. Min Act: -0.0006

Data Index: 433553 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0685. Min Act: -0.0006

Data Index: 778607 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0682. Min Act: -0.0006

Data Index: 262698 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0682. Min Act: -0.0006

Data Index: 1050064 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0673. Min Act: -0.0006

Data Index: 297972 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0683. Min Act: -0.0005

Data Index: 145553 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0643. Min Act: -0.0005

Data Index: 672812 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0599. Min Act: -0.0006

Data Index: 801440 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0595. Min Act: -0.0005

Data Index: 1870 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0585. Min Act: -0.0006

Data Index: 625759 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0581. Min Act: -0.0006

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0580. Min Act: -0.0006

Data Index: 981016 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0563. Min Act: -0.0006

Data Index: 657809 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0560. Min Act: -0.0006

Data Index: 92619 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0556. Min Act: -0.0005

Data Index: 1297645 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0533. Min Act: -0.0006

Data Index: 129275 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0554. Min Act: -0.0006

Data Index: 1117377 (C4 (Web Text))

Max Activating Token Index: 129