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

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

Neuron 2221 in Layer 1

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: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0002

Data Index: 1543552 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1558. Min Act: -0.0002

Data Index: 1552357 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1563. Min Act: -0.0002

Data Index: 1643508 (Python Code)

Max Activating Token Index: 287

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1525. Min Act: -0.0002

Data Index: 1556523 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1505. Min Act: -0.0002

Data Index: 1554909 (Python Code)

Max Activating Token Index: 487

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1502. Min Act: -0.0002

Data Index: 1614789 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1479. Min Act: -0.0002

Data Index: 1568281 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1495. Min Act: -0.0002

Data Index: 1388348 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1490. Min Act: -0.0002

Data Index: 1598755 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1480. Min Act: -0.0002

Data Index: 1635601 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1484. Min Act: -0.0002

Data Index: 1600627 (Python Code)

Max Activating Token Index: 216

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1510. Min Act: -0.0002

Data Index: 1548761 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1642809 (Python Code)

Max Activating Token Index: 709

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1452. Min Act: -0.0002

Data Index: 1431772 (Python Code)

Max Activating Token Index: 276

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1457. Min Act: -0.0002

Data Index: 1566892 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1509721 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1590216 (Python Code)

Max Activating Token Index: 595

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1590358 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1467. Min Act: -0.0002

Data Index: 1454287 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1442. Min Act: -0.0002

Data Index: 1592658 (Python Code)

Max Activating Token Index: 161