Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5682 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0002

Data Index: 526686 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1201384 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0768. Min Act: -0.0002

Data Index: 112529 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1320640 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0697. Min Act: -0.0002

Data Index: 468973 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0682. Min Act: -0.0002

Data Index: 400877 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0625. Min Act: -0.0002

Data Index: 757609 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0633. Min Act: -0.0002

Data Index: 570737 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0657. Min Act: -0.0002

Data Index: 439763 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0655. Min Act: -0.0002

Data Index: 512875 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0681. Min Act: -0.0002

Data Index: 670104 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0656. Min Act: -0.0002

Data Index: 905679 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0651. Min Act: -0.0002

Data Index: 544141 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0669. Min Act: -0.0002

Data Index: 436207 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1179871 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0633. Min Act: -0.0002

Data Index: 987015 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0650. Min Act: -0.0002

Data Index: 630924 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1058702 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0666. Min Act: -0.0002

Data Index: 334021 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1078786 (C4 (Web Text))

Max Activating Token Index: 242