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

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

Neuron 468 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: 0.0682. Min Range: -0.0682

Max Act: 0.0668. Min Act: -0.0005

Data Index: 711942 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0671. Min Act: -0.0005

Data Index: 199358 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0682. Min Act: -0.0005

Data Index: 489814 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0646. Min Act: -0.0005

Data Index: 788936 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0657. Min Act: -0.0005

Data Index: 510484 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0661. Min Act: -0.0005

Data Index: 796166 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0663. Min Act: -0.0005

Data Index: 897117 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0659. Min Act: -0.0005

Data Index: 856802 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0641. Min Act: -0.0005

Data Index: 1285042 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0643. Min Act: -0.0005

Data Index: 735122 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0626. Min Act: -0.0005

Data Index: 1177744 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0619. Min Act: -0.0005

Data Index: 76889 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0625. Min Act: -0.0005

Data Index: 342420 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0620. Min Act: -0.0005

Data Index: 1298946 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0607. Min Act: -0.0005

Data Index: 444521 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0596. Min Act: -0.0005

Data Index: 1053041 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0593. Min Act: -0.0005

Data Index: 888002 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0600. Min Act: -0.0005

Data Index: 619531 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0608. Min Act: -0.0005

Data Index: 657837 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.0682. Min Range: -0.0682

Max Act: 0.0556. Min Act: -0.0005

Data Index: 9792 (C4 (Web Text))

Max Activating Token Index: 834