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

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

Neuron 332 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: 3.4122. Min Range: -3.4122

Max Act: 3.4122. Min Act: -0.1700

Data Index: 1566493 (Python Code)

Max Activating Token Index: 358

Text #1

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.3116. Min Act: -0.1699

Data Index: 1613491 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.3016. Min Act: -0.1700

Data Index: 1589745 (Python Code)

Max Activating Token Index: 435

Text #3

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.2370. Min Act: -0.1700

Data Index: 1432119 (Python Code)

Max Activating Token Index: 489

Text #4

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1828. Min Act: -0.1700

Data Index: 1577099 (Python Code)

Max Activating Token Index: 699

Text #5

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1753. Min Act: -0.1700

Data Index: 1443610 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1881. Min Act: -0.1699

Data Index: 1362151 (Python Code)

Max Activating Token Index: 241

Text #7

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1834. Min Act: -0.1700

Data Index: 1412302 (Python Code)

Max Activating Token Index: 221

Text #8

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1789. Min Act: -0.1700

Data Index: 1516354 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1658. Min Act: -0.1700

Data Index: 1430558 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1452. Min Act: -0.1700

Data Index: 1393537 (Python Code)

Max Activating Token Index: 1003

Text #11

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1623267 (Python Code)

Max Activating Token Index: 408

Text #12

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1548. Min Act: -0.1700

Data Index: 264241 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1133. Min Act: -0.1700

Data Index: 1592203 (Python Code)

Max Activating Token Index: 215

Text #14

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1464. Min Act: -0.1700

Data Index: 1645880 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1480667 (Python Code)

Max Activating Token Index: 844

Text #16

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1108. Min Act: -0.1700

Data Index: 1462748 (Python Code)

Max Activating Token Index: 393

Text #17

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1173. Min Act: -0.1700

Data Index: 1492465 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1091. Min Act: -0.1700

Data Index: 607639 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 3.4122. Min Range: -3.4122

Max Act: 3.1208. Min Act: -0.1700

Data Index: 1398102 (Python Code)

Max Activating Token Index: 1014