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

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

Neuron 770 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: 0.0770. Min Range: -0.0770

Max Act: 0.0770. Min Act: -0.0002

Data Index: 650087 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1265631 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0731. Min Act: -0.0002

Data Index: 954603 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0693. Min Act: -0.0002

Data Index: 626262 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0703. Min Act: -0.0002

Data Index: 451426 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0676. Min Act: -0.0002

Data Index: 707420 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0668. Min Act: -0.0002

Data Index: 942862 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1062300 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0649. Min Act: -0.0002

Data Index: 196210 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0654. Min Act: -0.0002

Data Index: 546640 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0647. Min Act: -0.0002

Data Index: 56644 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1013414 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1255514 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0655. Min Act: -0.0002

Data Index: 812171 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0644. Min Act: -0.0002

Data Index: 745223 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0644. Min Act: -0.0002

Data Index: 566904 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0640. Min Act: -0.0001

Data Index: 973528 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0660. Min Act: -0.0002

Data Index: 70142 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0624. Min Act: -0.0002

Data Index: 474956 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.0770. Min Range: -0.0770

Max Act: 0.0645. Min Act: -0.0002

Data Index: 186683 (C4 (Web Text))

Max Activating Token Index: 260