Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 355 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1072678 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1343141 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0627. Min Act: -0.0001

Data Index: 762203 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0688. Min Act: -0.0001

Data Index: 905040 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0688. Min Act: -0.0001

Data Index: 245791 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0676. Min Act: -0.0001

Data Index: 682339 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0672. Min Act: -0.0001

Data Index: 632753 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0701. Min Act: -0.0001

Data Index: 988863 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1225132 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0657. Min Act: -0.0001

Data Index: 369993 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1255492 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1178972 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0597. Min Act: -0.0001

Data Index: 685623 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0673. Min Act: -0.0001

Data Index: 4457 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0681. Min Act: -0.0001

Data Index: 202659 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0673. Min Act: -0.0001

Data Index: 470545 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0588. Min Act: -0.0001

Data Index: 325145 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0726. Min Act: -0.0001

Data Index: 667657 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0663. Min Act: -0.0001

Data Index: 1313105 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1181527 (C4 (Web Text))

Max Activating Token Index: 14