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

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

Neuron 25 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1637507 (Python Code)

Max Activating Token Index: 201

Text #1

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1397770 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1437609 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1587953 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1570991 (Python Code)

Max Activating Token Index: 93

Text #5

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1504601 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1565272 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1440282 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1485907 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1603821 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1654279 (Python Code)

Max Activating Token Index: 222

Text #11

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1374009 (Python Code)

Max Activating Token Index: 159

Text #12

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1634288 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1481769 (Python Code)

Max Activating Token Index: 893

Text #14

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1614309 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1369997 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1434. Min Act: -0.0001

Data Index: 1643879 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1555276 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1451. Min Act: -0.0001

Data Index: 1465797 (Python Code)

Max Activating Token Index: 876

Text #19

Max Range: 0.1765. Min Range: -0.1765

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1560146 (Python Code)

Max Activating Token Index: 327