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

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

Neuron 1628 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1586227 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1497470 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1370817 (Python Code)

Max Activating Token Index: 948

Text #3

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1539052 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1525. Min Act: -0.0001

Data Index: 1527648 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1527865 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1462233 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1652521 (Python Code)

Max Activating Token Index: 734

Text #8

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1635315 (Python Code)

Max Activating Token Index: 893

Text #9

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1627113 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1587285 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1554543 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1477. Min Act: -0.0002

Data Index: 1416086 (Python Code)

Max Activating Token Index: 37

Text #13

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1375886 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1374268 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1453. Min Act: -0.0002

Data Index: 1435521 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1510550 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1556813 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1643040 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1642951 (Python Code)

Max Activating Token Index: 697