Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 22 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1829. Min Act: -0.0002

Data Index: 1466123 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1652. Min Act: -0.0003

Data Index: 1494784 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1592. Min Act: -0.0003

Data Index: 1559701 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1516. Min Act: -0.0004

Data Index: 1557933 (Python Code)

Max Activating Token Index: 331

Text #4

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1526. Min Act: -0.0003

Data Index: 1433486 (Python Code)

Max Activating Token Index: 427

Text #5

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1512. Min Act: -0.0003

Data Index: 1445718 (Python Code)

Max Activating Token Index: 342

Text #6

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1654. Min Act: -0.0003

Data Index: 1468706 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1541. Min Act: -0.0002

Data Index: 1593549 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1502. Min Act: -0.0003

Data Index: 1594589 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1485. Min Act: -0.0003

Data Index: 1439008 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1474. Min Act: -0.0003

Data Index: 1590950 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1494. Min Act: -0.0003

Data Index: 1501695 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1432. Min Act: -0.0003

Data Index: 1402169 (Python Code)

Max Activating Token Index: 263

Text #13

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1476. Min Act: -0.0003

Data Index: 1508500 (Python Code)

Max Activating Token Index: 586

Text #14

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1407. Min Act: -0.0003

Data Index: 1387041 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1405. Min Act: -0.0003

Data Index: 1473660 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1483. Min Act: -0.0003

Data Index: 1368418 (Python Code)

Max Activating Token Index: 564

Text #17

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1444. Min Act: -0.0003

Data Index: 1531666 (Python Code)

Max Activating Token Index: 456

Text #18

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1448. Min Act: -0.0003

Data Index: 1602766 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1447. Min Act: -0.0003

Data Index: 1631639 (Python Code)

Max Activating Token Index: 83