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

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

Neuron 1224 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: 4.3116. Min Range: -4.3116

Max Act: 4.3116. Min Act: -0.1700

Data Index: 1368075 (Python Code)

Max Activating Token Index: 249

Text #1

Max Range: 4.3116. Min Range: -4.3116

Max Act: 4.1257. Min Act: -0.1699

Data Index: 1534330 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.9916. Min Act: -0.1700

Data Index: 1522951 (Python Code)

Max Activating Token Index: 658

Text #3

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.9711. Min Act: -0.1698

Data Index: 1497889 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.9767. Min Act: -0.1694

Data Index: 1492261 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.9867. Min Act: -0.1700

Data Index: 1390993 (Python Code)

Max Activating Token Index: 546

Text #6

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.9024. Min Act: -0.1694

Data Index: 992333 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.9335. Min Act: -0.1699

Data Index: 1407709 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.8910. Min Act: -0.1688

Data Index: 1530150 (Python Code)

Max Activating Token Index: 118

Text #9

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.8861. Min Act: -0.1700

Data Index: 1542363 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.8358. Min Act: -0.1603

Data Index: 1620289 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1459195 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.8156. Min Act: -0.1700

Data Index: 1629849 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.7846. Min Act: -0.1700

Data Index: 1496522 (Python Code)

Max Activating Token Index: 615

Text #14

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.7760. Min Act: -0.1401

Data Index: 1462781 (Python Code)

Max Activating Token Index: 666

Text #15

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.7822. Min Act: -0.1700

Data Index: 1487093 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.7715. Min Act: -0.1700

Data Index: 1115772 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.7751. Min Act: -0.1699

Data Index: 1526625 (Python Code)

Max Activating Token Index: 610

Text #18

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.7515. Min Act: -0.1697

Data Index: 1652538 (Python Code)

Max Activating Token Index: 276

Text #19

Max Range: 4.3116. Min Range: -4.3116

Max Act: 3.7559. Min Act: -0.1700

Data Index: 1409607 (Python Code)

Max Activating Token Index: 878