Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1359 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.0018. Min Range: -4.0018

Max Act: 4.0018. Min Act: -0.1697

Data Index: 1487263 (Python Code)

Max Activating Token Index: 707

Text #1

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.9592. Min Act: -0.1699

Data Index: 1410100 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.8890. Min Act: -0.1685

Data Index: 1363500 (Python Code)

Max Activating Token Index: 753

Text #3

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.8776. Min Act: -0.1700

Data Index: 1520915 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.8650. Min Act: -0.1700

Data Index: 1522880 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.8645. Min Act: -0.1697

Data Index: 1472981 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.8373. Min Act: -0.1683

Data Index: 1551928 (Python Code)

Max Activating Token Index: 303

Text #7

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.8217. Min Act: -0.1694

Data Index: 1562267 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7478. Min Act: -0.1699

Data Index: 1396791 (Python Code)

Max Activating Token Index: 523

Text #9

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7235. Min Act: -0.1611

Data Index: 1486746 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7425. Min Act: -0.1699

Data Index: 1515846 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7354. Min Act: -0.1700

Data Index: 1612505 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7467. Min Act: -0.1689

Data Index: 1566805 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7377. Min Act: -0.1570

Data Index: 1565362 (Python Code)

Max Activating Token Index: 352

Text #14

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7379. Min Act: -0.1665

Data Index: 1567720 (Python Code)

Max Activating Token Index: 583

Text #15

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7389. Min Act: -0.1577

Data Index: 1587830 (Python Code)

Max Activating Token Index: 1006

Text #16

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7269. Min Act: -0.1685

Data Index: 1638272 (Python Code)

Max Activating Token Index: 128

Text #17

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7321. Min Act: -0.1698

Data Index: 1519653 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7127. Min Act: -0.1350

Data Index: 1570419 (Python Code)

Max Activating Token Index: 762

Text #19

Max Range: 4.0018. Min Range: -4.0018

Max Act: 3.7111. Min Act: -0.1700

Data Index: 1375275 (Python Code)

Max Activating Token Index: 747