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

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

Neuron 2485 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1778. Min Act: -0.0001

Data Index: 1497549 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.2363. Min Act: -0.0001

Data Index: 1523831 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1636. Min Act: -0.0001

Data Index: 1399637 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.2480. Min Act: -0.0001

Data Index: 1442803 (Python Code)

Max Activating Token Index: 480

Text #4

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.2631. Min Act: -0.0001

Data Index: 1390420 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1500. Min Act: -0.0001

Data Index: 1608733 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1407. Min Act: -0.0001

Data Index: 1534847 (Python Code)

Max Activating Token Index: 661

Text #7

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1637. Min Act: -0.0001

Data Index: 1421949 (Python Code)

Max Activating Token Index: 1003

Text #8

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1446096 (Python Code)

Max Activating Token Index: 211

Text #9

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1941. Min Act: -0.0001

Data Index: 1360274 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1968. Min Act: -0.0001

Data Index: 760601 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1474. Min Act: -0.0001

Data Index: 1635763 (Python Code)

Max Activating Token Index: 885

Text #12

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1151. Min Act: -0.0001

Data Index: 1538879 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1000. Min Act: -0.0001

Data Index: 1547601 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1843. Min Act: -0.0001

Data Index: 1523120 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1839. Min Act: -0.0001

Data Index: 1406883 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.1584. Min Act: -0.0001

Data Index: 1454512 (Python Code)

Max Activating Token Index: 663

Text #17

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0824. Min Act: -0.0001

Data Index: 1642025 (Python Code)

Max Activating Token Index: 510

Text #18

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0921. Min Act: -0.0001

Data Index: 1387721 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 1.2631. Min Range: -1.2631

Max Act: 1.0479. Min Act: -0.0001

Data Index: 1504167 (Python Code)

Max Activating Token Index: 332