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

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

Neuron 1874 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.3672. Min Act: -0.1700

Data Index: 1479948 (Python Code)

Max Activating Token Index: 344

Text #1

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.2415. Min Act: -0.1700

Data Index: 1578151 (Python Code)

Max Activating Token Index: 320

Text #2

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1943. Min Act: -0.1700

Data Index: 1577261 (Python Code)

Max Activating Token Index: 376

Text #3

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1786. Min Act: -0.1700

Data Index: 1483478 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1471. Min Act: -0.1700

Data Index: 1580168 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1314. Min Act: -0.1700

Data Index: 1644609 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1448890 (Python Code)

Max Activating Token Index: 351

Text #7

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1559057 (Python Code)

Max Activating Token Index: 454

Text #8

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1314. Min Act: -0.1700

Data Index: 1626533 (Python Code)

Max Activating Token Index: 528

Text #9

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0998. Min Act: -0.1700

Data Index: 1580934 (Python Code)

Max Activating Token Index: 709

Text #10

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1397257 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0998. Min Act: -0.1700

Data Index: 1546032 (Python Code)

Max Activating Token Index: 732

Text #12

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0841. Min Act: -0.1700

Data Index: 1597693 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1387211 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0841. Min Act: -0.1700

Data Index: 1619987 (Python Code)

Max Activating Token Index: 257

Text #15

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0525. Min Act: -0.1700

Data Index: 1422484 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1618348 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1611178 (Python Code)

Max Activating Token Index: 488

Text #18

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1433759 (Python Code)

Max Activating Token Index: 169

Text #19

Max Range: 3.3672. Min Range: -3.3672

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1462340 (Python Code)

Max Activating Token Index: 450