Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2363. Min Act: -0.0001

Data Index: 249678 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1267897 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1886. Min Act: -0.0001

Data Index: 744035 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1266877 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1753. Min Act: -0.0001

Data Index: 317441 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1912. Min Act: -0.0001

Data Index: 459853 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1891. Min Act: -0.0001

Data Index: 865415 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1947. Min Act: -0.0001

Data Index: 142826 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1867. Min Act: -0.0001

Data Index: 317548 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1839. Min Act: -0.0001

Data Index: 379416 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1813. Min Act: -0.0001

Data Index: 429411 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1682. Min Act: -0.0001

Data Index: 206798 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1708. Min Act: -0.0001

Data Index: 520299 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1765. Min Act: -0.0001

Data Index: 409541 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1020690 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1422. Min Act: -0.0001

Data Index: 260690 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1812. Min Act: -0.0001

Data Index: 682202 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1479. Min Act: -0.0001

Data Index: 796604 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1726. Min Act: -0.0001

Data Index: 387536 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1760. Min Act: -0.0001

Data Index: 163307 (C4 (Web Text))

Max Activating Token Index: 111