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

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

Neuron 1957 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: 0.0926. Min Range: -0.0926

Max Act: 0.0926. Min Act: -0.0001

Data Index: 749683 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1328827 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1056978 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0787. Min Act: -0.0002

Data Index: 566146 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0817. Min Act: -0.0002

Data Index: 153131 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0773. Min Act: -0.0002

Data Index: 198353 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0819. Min Act: -0.0002

Data Index: 584034 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1210620 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0800. Min Act: -0.0002

Data Index: 29307 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0795. Min Act: -0.0002

Data Index: 15125 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1271665 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0778. Min Act: -0.0002

Data Index: 395672 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0825. Min Act: -0.0002

Data Index: 511314 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0767. Min Act: -0.0002

Data Index: 596997 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0780. Min Act: -0.0002

Data Index: 871153 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1337203 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1301901 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0767. Min Act: -0.0002

Data Index: 320353 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0772. Min Act: -0.0002

Data Index: 513041 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0926. Min Range: -0.0926

Max Act: 0.0762. Min Act: -0.0002

Data Index: 507869 (C4 (Web Text))

Max Activating Token Index: 11