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

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

Neuron 1523 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.3883. Min Act: -0.0002

Data Index: 1552890 (Python Code)

Max Activating Token Index: 588

Text #1

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.2710. Min Act: -0.0002

Data Index: 1475314 (Python Code)

Max Activating Token Index: 34

Text #2

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.2635. Min Act: -0.0002

Data Index: 1384559 (Python Code)

Max Activating Token Index: 208

Text #3

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1523. Min Act: -0.0002

Data Index: 1648161 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1078. Min Act: -0.0002

Data Index: 1490041 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.1044. Min Act: -0.0002

Data Index: 1424097 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.0163. Min Act: -0.0002

Data Index: 1471565 (Python Code)

Max Activating Token Index: 417

Text #7

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.0388. Min Act: -0.0002

Data Index: 1497517 (Python Code)

Max Activating Token Index: 144

Text #8

Max Range: 1.3883. Min Range: -1.3883

Max Act: 1.0102. Min Act: -0.0002

Data Index: 1644928 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.9321. Min Act: -0.0002

Data Index: 1401158 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.8891. Min Act: -0.0002

Data Index: 1502160 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.8729. Min Act: -0.0002

Data Index: 1531588 (Python Code)

Max Activating Token Index: 588

Text #12

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.8756. Min Act: -0.0002

Data Index: 1374509 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.8842. Min Act: -0.0002

Data Index: 1470198 (Python Code)

Max Activating Token Index: 836

Text #14

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.8719. Min Act: -0.0002

Data Index: 1442051 (Python Code)

Max Activating Token Index: 303

Text #15

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.8501. Min Act: -0.0002

Data Index: 1373506 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.8155. Min Act: -0.0002

Data Index: 1535622 (Python Code)

Max Activating Token Index: 795

Text #17

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.7624. Min Act: -0.0002

Data Index: 1393729 (Python Code)

Max Activating Token Index: 514

Text #18

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.7431. Min Act: -0.0002

Data Index: 1425634 (Python Code)

Max Activating Token Index: 457

Text #19

Max Range: 1.3883. Min Range: -1.3883

Max Act: 0.7413. Min Act: -0.0002

Data Index: 1380059 (Python Code)

Max Activating Token Index: 244