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

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

Neuron 3993 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: 0.6495. Min Range: -0.6495

Max Act: 0.6495. Min Act: -0.0000

Data Index: 76946 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6353. Min Act: -0.0000

Data Index: 706502 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.6022. Min Act: -0.0000

Data Index: 784404 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5336. Min Act: -0.0000

Data Index: 138239 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5927. Min Act: -0.0000

Data Index: 914908 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5589. Min Act: -0.0000

Data Index: 711847 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5548. Min Act: -0.0000

Data Index: 796201 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5422. Min Act: -0.0000

Data Index: 911970 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5152. Min Act: -0.0000

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4881. Min Act: -0.0000

Data Index: 969530 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.5011. Min Act: -0.0000

Data Index: 790229 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4762. Min Act: -0.0000

Data Index: 365835 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4745. Min Act: -0.0000

Data Index: 558223 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.3948. Min Act: -0.0000

Data Index: 233689 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4038. Min Act: -0.0000

Data Index: 262483 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.4027. Min Act: -0.0000

Data Index: 413160 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.3662. Min Act: -0.0000

Data Index: 970034 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.3739. Min Act: -0.0000

Data Index: 158399 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.3762. Min Act: -0.0000

Data Index: 925497 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.6495. Min Range: -0.6495

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1203990 (C4 (Web Text))

Max Activating Token Index: 604