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

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

Neuron 1524 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1630. Min Act: -0.0003

Data Index: 1439089 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1581. Min Act: -0.0003

Data Index: 1540966 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1556. Min Act: -0.0003

Data Index: 1565362 (Python Code)

Max Activating Token Index: 432

Text #3

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1553. Min Act: -0.0003

Data Index: 1439956 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1546. Min Act: -0.0003

Data Index: 1541634 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1508. Min Act: -0.0003

Data Index: 1482985 (Python Code)

Max Activating Token Index: 291

Text #6

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1509. Min Act: -0.0003

Data Index: 1602264 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1510. Min Act: -0.0003

Data Index: 1386817 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1508. Min Act: -0.0003

Data Index: 1553480 (Python Code)

Max Activating Token Index: 376

Text #9

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1504. Min Act: -0.0003

Data Index: 1576914 (Python Code)

Max Activating Token Index: 371

Text #10

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1532. Min Act: -0.0003

Data Index: 1502556 (Python Code)

Max Activating Token Index: 402

Text #11

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1528. Min Act: -0.0003

Data Index: 1437186 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1531. Min Act: -0.0003

Data Index: 1483422 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1551. Min Act: -0.0003

Data Index: 1426091 (Python Code)

Max Activating Token Index: 394

Text #14

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1523. Min Act: -0.0003

Data Index: 1430234 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1524. Min Act: -0.0003

Data Index: 1404655 (Python Code)

Max Activating Token Index: 487

Text #16

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1524. Min Act: -0.0003

Data Index: 1547591 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1522. Min Act: -0.0003

Data Index: 1615566 (Python Code)

Max Activating Token Index: 569

Text #18

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1518. Min Act: -0.0003

Data Index: 1421898 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 0.1630. Min Range: -0.1630

Max Act: 0.1520. Min Act: -0.0003

Data Index: 1488333 (Python Code)

Max Activating Token Index: 479