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

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

Neuron 5794 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1249496 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.5150. Min Act: -0.0000

Data Index: 646459 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4662. Min Act: -0.0000

Data Index: 988520 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4747. Min Act: -0.0000

Data Index: 935475 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1055760 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4243. Min Act: -0.0000

Data Index: 813146 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4305. Min Act: -0.0000

Data Index: 581777 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4429. Min Act: -0.0000

Data Index: 145365 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3651. Min Act: -0.0000

Data Index: 669834 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1096773 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3847. Min Act: -0.0000

Data Index: 489619 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3494. Min Act: -0.0000

Data Index: 561798 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3961. Min Act: -0.0000

Data Index: 61904 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3910. Min Act: -0.0000

Data Index: 324757 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3467. Min Act: -0.0000

Data Index: 627318 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1177977 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3832. Min Act: -0.0000

Data Index: 359458 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3510. Min Act: -0.0000

Data Index: 920989 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3604. Min Act: -0.0000

Data Index: 517368 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.5633. Min Range: -0.5633

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1121300 (C4 (Web Text))

Max Activating Token Index: 1020