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

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

Neuron 111 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0001

Data Index: 264599 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0812. Min Act: -0.0001

Data Index: 361331 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0794. Min Act: -0.0001

Data Index: 250647 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0699. Min Act: -0.0001

Data Index: 219507 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0700. Min Act: -0.0001

Data Index: 93256 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0687. Min Act: -0.0001

Data Index: 619598 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0698. Min Act: -0.0001

Data Index: 503342 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0653. Min Act: -0.0001

Data Index: 799311 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0619. Min Act: -0.0001

Data Index: 714854 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1298722 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0593. Min Act: -0.0001

Data Index: 106219 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0615. Min Act: -0.0001

Data Index: 366965 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0612. Min Act: -0.0001

Data Index: 466505 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0581. Min Act: -0.0001

Data Index: 773278 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0576. Min Act: -0.0001

Data Index: 905466 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0599. Min Act: -0.0001

Data Index: 729484 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0569. Min Act: -0.0001

Data Index: 100222 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0510. Min Act: -0.0001

Data Index: 821110 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0516. Min Act: -0.0001

Data Index: 205142 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1048464 (C4 (Web Text))

Max Activating Token Index: 814