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

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

Neuron 2383 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0691. Min Act: -0.0004

Data Index: 407299 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0709. Min Act: -0.0004

Data Index: 633 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0004

Data Index: 1186585 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0650. Min Act: -0.0004

Data Index: 255872 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0692. Min Act: -0.0004

Data Index: 864860 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0665. Min Act: -0.0004

Data Index: 89619 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0687. Min Act: -0.0004

Data Index: 9788 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0667. Min Act: -0.0004

Data Index: 493932 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0629. Min Act: -0.0004

Data Index: 777911 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0670. Min Act: -0.0004

Data Index: 1007351 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0668. Min Act: -0.0004

Data Index: 61204 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0633. Min Act: -0.0004

Data Index: 877157 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0641. Min Act: -0.0004

Data Index: 248449 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0629. Min Act: -0.0004

Data Index: 1182475 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0621. Min Act: -0.0004

Data Index: 428348 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0622. Min Act: -0.0004

Data Index: 128655 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0621. Min Act: -0.0004

Data Index: 863539 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0633. Min Act: -0.0004

Data Index: 768307 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0580. Min Act: -0.0004

Data Index: 903109 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0601. Min Act: -0.0004

Data Index: 512783 (C4 (Web Text))

Max Activating Token Index: 143