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

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

Neuron 1890 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0427. Min Range: -1.0427

Max Act: 1.0427. Min Act: -0.0001

Data Index: 1656093 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.9364. Min Act: -0.0001

Data Index: 1479551 (Python Code)

Max Activating Token Index: 692

Text #2

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.8335. Min Act: -0.0001

Data Index: 1630751 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7378. Min Act: -0.0001

Data Index: 1456212 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7750. Min Act: -0.0001

Data Index: 1448332 (Python Code)

Max Activating Token Index: 1019

Text #5

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.8262. Min Act: -0.0001

Data Index: 1498710 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7622. Min Act: -0.0001

Data Index: 1521858 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1507806 (Python Code)

Max Activating Token Index: 618

Text #8

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7451. Min Act: -0.0001

Data Index: 1559478 (Python Code)

Max Activating Token Index: 884

Text #9

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7527. Min Act: -0.0001

Data Index: 1501210 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6629. Min Act: -0.0001

Data Index: 1624558 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7053. Min Act: -0.0001

Data Index: 1585943 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6445. Min Act: -0.0001

Data Index: 1493452 (Python Code)

Max Activating Token Index: 502

Text #13

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6250. Min Act: -0.0001

Data Index: 1444226 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.5446. Min Act: -0.0001

Data Index: 1469718 (Python Code)

Max Activating Token Index: 287

Text #15

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.7455. Min Act: -0.0001

Data Index: 1419388 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1476889 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6595. Min Act: -0.0001

Data Index: 1417723 (Python Code)

Max Activating Token Index: 662

Text #18

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1548964 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 1.0427. Min Range: -1.0427

Max Act: 0.6238. Min Act: -0.0001

Data Index: 1613969 (Python Code)

Max Activating Token Index: 856