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

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

Neuron 2991 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: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1147568 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0620. Min Act: -0.0000

Data Index: 277310 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0621. Min Act: -0.0000

Data Index: 95430 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0605. Min Act: -0.0000

Data Index: 890913 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0569. Min Act: -0.0000

Data Index: 1077156 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1564069 (Python Code)

Max Activating Token Index: 742

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0517. Min Act: -0.0000

Data Index: 271747 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0550. Min Act: -0.0001

Data Index: 819600 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1623224 (Python Code)

Max Activating Token Index: 307

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0510. Min Act: -0.0000

Data Index: 75608 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0513. Min Act: -0.0000

Data Index: 1073789 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0447. Min Act: -0.0000

Data Index: 44082 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0462. Min Act: -0.0000

Data Index: 337784 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1651799 (Python Code)

Max Activating Token Index: 491

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0492. Min Act: -0.0000

Data Index: 342583 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0432. Min Act: -0.0000

Data Index: 364953 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1341037 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0427. Min Act: -0.0000

Data Index: 99204 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0464. Min Act: -0.0000

Data Index: 213152 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0452. Min Act: -0.0001

Data Index: 394000 (C4 (Web Text))

Max Activating Token Index: 753