Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2291 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0778. Min Act: -0.0002

Data Index: 743452 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0742. Min Act: -0.0002

Data Index: 60978 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0734. Min Act: -0.0002

Data Index: 841407 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1110146 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0707. Min Act: -0.0002

Data Index: 1315388 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0718. Min Act: -0.0002

Data Index: 462826 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0695. Min Act: -0.0002

Data Index: 790251 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1153447 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0692. Min Act: -0.0002

Data Index: 819988 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0685. Min Act: -0.0002

Data Index: 539649 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0672. Min Act: -0.0002

Data Index: 497494 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0683. Min Act: -0.0002

Data Index: 934452 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0682. Min Act: -0.0002

Data Index: 156210 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0666. Min Act: -0.0002

Data Index: 799115 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0672. Min Act: -0.0002

Data Index: 301797 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0668. Min Act: -0.0002

Data Index: 599932 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1133062 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0660. Min Act: -0.0002

Data Index: 582276 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1188586 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.0778. Min Range: -0.0778

Max Act: 0.0651. Min Act: -0.0002

Data Index: 249177 (C4 (Web Text))

Max Activating Token Index: 511