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

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

Neuron 2013 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0871. Min Range: -4.0871

Max Act: 4.0871. Min Act: -0.1699

Data Index: 1540353 (Python Code)

Max Activating Token Index: 975

Text #1

Max Range: 4.0871. Min Range: -4.0871

Max Act: 4.0245. Min Act: -0.1700

Data Index: 234812 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9776. Min Act: -0.1700

Data Index: 863351 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 4.0871. Min Range: -4.0871

Max Act: 4.0245. Min Act: -0.1700

Data Index: 1574648 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9464. Min Act: -0.1700

Data Index: 1645733 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9776. Min Act: -0.1700

Data Index: 1426267 (Python Code)

Max Activating Token Index: 614

Text #6

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9620. Min Act: -0.1699

Data Index: 1451609 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9307. Min Act: -0.1700

Data Index: 1361869 (Python Code)

Max Activating Token Index: 830

Text #8

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9307. Min Act: -0.1700

Data Index: 1462576 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9151. Min Act: -0.1700

Data Index: 473980 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9151. Min Act: -0.1700

Data Index: 704975 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9307. Min Act: -0.1700

Data Index: 931940 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9151. Min Act: -0.1699

Data Index: 1361444 (Python Code)

Max Activating Token Index: 66

Text #13

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9151. Min Act: -0.1700

Data Index: 1512892 (Python Code)

Max Activating Token Index: 843

Text #14

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.8838. Min Act: -0.1700

Data Index: 1576327 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9464. Min Act: -0.1699

Data Index: 1638805 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.8995. Min Act: -0.1699

Data Index: 1520153 (Python Code)

Max Activating Token Index: 723

Text #17

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.9151. Min Act: -0.1700

Data Index: 1383083 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.8526. Min Act: -0.1700

Data Index: 1490828 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 4.0871. Min Range: -4.0871

Max Act: 3.8995. Min Act: -0.1700

Data Index: 1459414 (Python Code)

Max Activating Token Index: 758