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

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

Neuron 4514 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3961. Min Range: -1.3961

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1402801 (Python Code)

Max Activating Token Index: 584

Text #1

Max Range: 1.3961. Min Range: -1.3961

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1471298 (Python Code)

Max Activating Token Index: 819

Text #2

Max Range: 1.3961. Min Range: -1.3961

Max Act: 1.1155. Min Act: 0.0002

Data Index: 1403116 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 1.3961. Min Range: -1.3961

Max Act: 1.0000. Min Act: 0.0001

Data Index: 1523559 (Python Code)

Max Activating Token Index: 301

Text #4

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.9484. Min Act: -0.0000

Data Index: 1551228 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1429326 (Python Code)

Max Activating Token Index: 157

Text #6

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.9135. Min Act: 0.0002

Data Index: 1508725 (Python Code)

Max Activating Token Index: 32

Text #7

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.9517. Min Act: 0.0000

Data Index: 1444362 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1480389 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1619933 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.8992. Min Act: 0.0000

Data Index: 1625841 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1649216 (Python Code)

Max Activating Token Index: 638

Text #12

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1452356 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.7619. Min Act: 0.0000

Data Index: 1600015 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.7807. Min Act: 0.0001

Data Index: 1455818 (Python Code)

Max Activating Token Index: 915

Text #15

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.7865. Min Act: 0.0000

Data Index: 1445913 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1610576 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1369952 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.7133. Min Act: 0.0002

Data Index: 1366860 (Python Code)

Max Activating Token Index: 601

Text #19

Max Range: 1.3961. Min Range: -1.3961

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1437865 (Python Code)

Max Activating Token Index: 986