Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2994 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.7572. Min Act: -0.0000

Data Index: 1651905 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.8447. Min Act: 0.0000

Data Index: 1544276 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.8113. Min Act: -0.0000

Data Index: 1466775 (Python Code)

Max Activating Token Index: 185

Text #3

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.6167. Min Act: -0.0000

Data Index: 1555535 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.3975. Min Act: -0.0000

Data Index: 1519891 (Python Code)

Max Activating Token Index: 119

Text #5

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.1583. Min Act: -0.0000

Data Index: 1538895 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.2125. Min Act: -0.0000

Data Index: 1536002 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.0716. Min Act: 0.0000

Data Index: 1475394 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.2602. Min Act: -0.0000

Data Index: 1415413 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.0186. Min Act: -0.0000

Data Index: 1409959 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 2.8447. Min Range: -2.8447

Max Act: 2.0093. Min Act: -0.0001

Data Index: 1514674 (Python Code)

Max Activating Token Index: 644

Text #11

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.9306. Min Act: -0.0000

Data Index: 1370355 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.9302. Min Act: -0.0000

Data Index: 1475517 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.7822. Min Act: -0.0000

Data Index: 1517461 (Python Code)

Max Activating Token Index: 911

Text #14

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.8621. Min Act: -0.0000

Data Index: 1387388 (Python Code)

Max Activating Token Index: 361

Text #15

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.8352. Min Act: -0.0000

Data Index: 1590744 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.9341. Min Act: -0.0000

Data Index: 1606020 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.8437. Min Act: -0.0001

Data Index: 1496373 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.7264. Min Act: -0.0001

Data Index: 1395642 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 2.8447. Min Range: -2.8447

Max Act: 1.8295. Min Act: -0.0000

Data Index: 1472807 (Python Code)

Max Activating Token Index: 463