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

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

Neuron 1704 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.3936. Min Act: -0.1700

Data Index: 1485293 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1478035 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1437505 (Python Code)

Max Activating Token Index: 571

Text #3

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2061. Min Act: -0.1700

Data Index: 1391847 (Python Code)

Max Activating Token Index: 570

Text #4

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2373. Min Act: -0.1700

Data Index: 1366585 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2373. Min Act: -0.1700

Data Index: 1643843 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.1436. Min Act: -0.1700

Data Index: 1595897 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.1748. Min Act: -0.1700

Data Index: 1510044 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2373. Min Act: -0.1700

Data Index: 1548143 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.3311. Min Act: -0.1700

Data Index: 1650927 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2061. Min Act: -0.1700

Data Index: 1631574 (Python Code)

Max Activating Token Index: 732

Text #11

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2061. Min Act: -0.1700

Data Index: 1588807 (Python Code)

Max Activating Token Index: 660

Text #12

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2373. Min Act: -0.1700

Data Index: 1423147 (Python Code)

Max Activating Token Index: 479

Text #13

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1580443 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1558595 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.1748. Min Act: -0.1700

Data Index: 1539359 (Python Code)

Max Activating Token Index: 859

Text #16

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.1436. Min Act: -0.1700

Data Index: 1545669 (Python Code)

Max Activating Token Index: 352

Text #17

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2061. Min Act: -0.1700

Data Index: 1392459 (Python Code)

Max Activating Token Index: 649

Text #18

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.2998. Min Act: -0.1700

Data Index: 1422918 (Python Code)

Max Activating Token Index: 868

Text #19

Max Range: 5.3936. Min Range: -5.3936

Max Act: 5.1436. Min Act: -0.1700

Data Index: 1486521 (Python Code)

Max Activating Token Index: 709