Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 855 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.2690. Min Act: -0.1700

Data Index: 706956 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.2218. Min Act: -0.1700

Data Index: 1401723 (Python Code)

Max Activating Token Index: 555

Text #2

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1415042 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1401141 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1007046 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1402679 (Python Code)

Max Activating Token Index: 307

Text #6

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1525254 (Python Code)

Max Activating Token Index: 182

Text #7

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1361929 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1613623 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1537836 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1509545 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1589. Min Act: -0.1700

Data Index: 1550670 (Python Code)

Max Activating Token Index: 657

Text #12

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1649478 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1576639 (Python Code)

Max Activating Token Index: 553

Text #14

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1746. Min Act: -0.1700

Data Index: 1566682 (Python Code)

Max Activating Token Index: 376

Text #15

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1904. Min Act: -0.1700

Data Index: 1582961 (Python Code)

Max Activating Token Index: 406

Text #16

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1589. Min Act: -0.1700

Data Index: 1426575 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1589. Min Act: -0.1700

Data Index: 1508952 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1274. Min Act: -0.1700

Data Index: 769700 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 3.2690. Min Range: -3.2690

Max Act: 3.1116. Min Act: -0.1700

Data Index: 1559633 (Python Code)

Max Activating Token Index: 485