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

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

Neuron 553 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1071860 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1300927 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0577. Min Act: -0.0000

Data Index: 940878 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0524. Min Act: -0.0000

Data Index: 787866 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0498. Min Act: -0.0000

Data Index: 56702 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0446. Min Act: -0.0000

Data Index: 514506 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0467. Min Act: -0.0001

Data Index: 630729 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0439. Min Act: -0.0000

Data Index: 531171 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0445. Min Act: -0.0000

Data Index: 761114 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0410. Min Act: -0.0000

Data Index: 738763 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1465643 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1350238 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1215467 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0359. Min Act: -0.0001

Data Index: 576696 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1302347 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0390. Min Act: -0.0001

Data Index: 704062 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0387. Min Act: -0.0000

Data Index: 1124363 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0389. Min Act: -0.0000

Data Index: 955974 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1418972 (Python Code)

Max Activating Token Index: 613

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0382. Min Act: -0.0000

Data Index: 710476 (C4 (Web Text))

Max Activating Token Index: 380