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

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

Neuron 56 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0002

Data Index: 429936 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1292596 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1271018 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0881. Min Act: -0.0002

Data Index: 984877 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0873. Min Act: -0.0002

Data Index: 324639 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1160105 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0872. Min Act: -0.0002

Data Index: 424744 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0881. Min Act: -0.0001

Data Index: 177820 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1249490 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0839. Min Act: -0.0002

Data Index: 575347 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0834. Min Act: -0.0002

Data Index: 445432 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0860. Min Act: -0.0001

Data Index: 307805 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0812. Min Act: -0.0002

Data Index: 455740 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1000088 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1202358 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1227243 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0786. Min Act: -0.0002

Data Index: 702860 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0793. Min Act: -0.0001

Data Index: 561268 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1165252 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0760. Min Act: -0.0002

Data Index: 696459 (C4 (Web Text))

Max Activating Token Index: 815