Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 823 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1550. Min Act: -0.0003

Data Index: 1619621 (Python Code)

Max Activating Token Index: 869

Text #1

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1502. Min Act: -0.0003

Data Index: 1616657 (Python Code)

Max Activating Token Index: 489

Text #2

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1505. Min Act: -0.0003

Data Index: 1567399 (Python Code)

Max Activating Token Index: 567

Text #3

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1459. Min Act: -0.0003

Data Index: 1446350 (Python Code)

Max Activating Token Index: 989

Text #4

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1473. Min Act: -0.0003

Data Index: 1506704 (Python Code)

Max Activating Token Index: 776

Text #5

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1466. Min Act: -0.0003

Data Index: 1490697 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1373. Min Act: -0.0003

Data Index: 1519735 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1412. Min Act: -0.0003

Data Index: 1651930 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1411. Min Act: -0.0003

Data Index: 1546868 (Python Code)

Max Activating Token Index: 735

Text #9

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1401. Min Act: -0.0003

Data Index: 1509316 (Python Code)

Max Activating Token Index: 860

Text #10

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1385. Min Act: -0.0003

Data Index: 1595764 (Python Code)

Max Activating Token Index: 668

Text #11

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1418. Min Act: -0.0003

Data Index: 1549086 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1389. Min Act: -0.0003

Data Index: 1511946 (Python Code)

Max Activating Token Index: 863

Text #13

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1390. Min Act: -0.0003

Data Index: 1611258 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1375. Min Act: -0.0003

Data Index: 1643431 (Python Code)

Max Activating Token Index: 399

Text #15

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1367. Min Act: -0.0003

Data Index: 1592319 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1414. Min Act: -0.0003

Data Index: 1375725 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1374. Min Act: -0.0003

Data Index: 1424522 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1354. Min Act: -0.0003

Data Index: 1498060 (Python Code)

Max Activating Token Index: 969

Text #19

Max Range: 0.1550. Min Range: -0.1550

Max Act: 0.1351. Min Act: -0.0003

Data Index: 1611253 (Python Code)

Max Activating Token Index: 761