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

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

Neuron 1679 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: 3.3354. Min Range: -3.3354

Max Act: 3.3354. Min Act: -0.1700

Data Index: 1590070 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.3060. Min Act: -0.1700

Data Index: 1429752 (Python Code)

Max Activating Token Index: 334

Text #2

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.3319. Min Act: -0.1700

Data Index: 1445865 (Python Code)

Max Activating Token Index: 66

Text #3

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.2855. Min Act: -0.1700

Data Index: 1387991 (Python Code)

Max Activating Token Index: 414

Text #4

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.2365. Min Act: -0.1699

Data Index: 1602475 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.2164. Min Act: -0.1699

Data Index: 1558286 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.2137. Min Act: -0.1700

Data Index: 1632165 (Python Code)

Max Activating Token Index: 976

Text #7

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1789. Min Act: -0.1700

Data Index: 1637955 (Python Code)

Max Activating Token Index: 884

Text #8

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1886. Min Act: -0.1700

Data Index: 1550606 (Python Code)

Max Activating Token Index: 554

Text #9

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1660. Min Act: -0.1700

Data Index: 1568186 (Python Code)

Max Activating Token Index: 112

Text #10

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1593. Min Act: -0.1700

Data Index: 1440789 (Python Code)

Max Activating Token Index: 274

Text #11

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1627. Min Act: -0.1700

Data Index: 1465887 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1593. Min Act: -0.1700

Data Index: 1608373 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1729. Min Act: -0.1700

Data Index: 1367282 (Python Code)

Max Activating Token Index: 670

Text #14

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1606. Min Act: -0.1700

Data Index: 1401186 (Python Code)

Max Activating Token Index: 698

Text #15

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1373. Min Act: -0.1700

Data Index: 1410504 (Python Code)

Max Activating Token Index: 919

Text #16

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1134. Min Act: -0.1700

Data Index: 1365664 (Python Code)

Max Activating Token Index: 266

Text #17

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.0996. Min Act: -0.1700

Data Index: 1545798 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.0852. Min Act: -0.1700

Data Index: 1479260 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 3.3354. Min Range: -3.3354

Max Act: 3.1117. Min Act: -0.1700

Data Index: 1476022 (Python Code)

Max Activating Token Index: 92