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

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

Neuron 180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.2876. Min Act: -0.1700

Data Index: 1557216 (Python Code)

Max Activating Token Index: 918

Text #1

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.2251. Min Act: -0.1700

Data Index: 1588540 (Python Code)

Max Activating Token Index: 362

Text #2

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.1938. Min Act: -0.1700

Data Index: 1436169 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.1938. Min Act: -0.1700

Data Index: 1632226 (Python Code)

Max Activating Token Index: 145

Text #4

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.1626. Min Act: -0.1700

Data Index: 1429265 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.1313. Min Act: -0.1700

Data Index: 1407771 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.1313. Min Act: -0.1700

Data Index: 1582527 (Python Code)

Max Activating Token Index: 711

Text #7

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.1626. Min Act: -0.1700

Data Index: 1535744 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.1001. Min Act: -0.1700

Data Index: 1527718 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0063. Min Act: -0.1700

Data Index: 1396242 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0376. Min Act: -0.1700

Data Index: 1451919 (Python Code)

Max Activating Token Index: 462

Text #11

Max Range: 7.2876. Min Range: -7.2876

Max Act: 6.9751. Min Act: -0.1700

Data Index: 1545368 (Python Code)

Max Activating Token Index: 416

Text #12

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0376. Min Act: -0.1700

Data Index: 1545464 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0376. Min Act: -0.1700

Data Index: 1556414 (Python Code)

Max Activating Token Index: 664

Text #14

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0063. Min Act: -0.1700

Data Index: 1590827 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 7.2876. Min Range: -7.2876

Max Act: 6.9751. Min Act: -0.1700

Data Index: 1505624 (Python Code)

Max Activating Token Index: 936

Text #16

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0376. Min Act: -0.1700

Data Index: 1515955 (Python Code)

Max Activating Token Index: 851

Text #17

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0063. Min Act: -0.1700

Data Index: 1448046 (Python Code)

Max Activating Token Index: 727

Text #18

Max Range: 7.2876. Min Range: -7.2876

Max Act: 6.9751. Min Act: -0.1700

Data Index: 1633707 (Python Code)

Max Activating Token Index: 253

Text #19

Max Range: 7.2876. Min Range: -7.2876

Max Act: 7.0376. Min Act: -0.1700

Data Index: 1650815 (Python Code)

Max Activating Token Index: 899