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

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

Neuron 186 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: 5.3815. Min Range: -5.3815

Max Act: 5.3815. Min Act: -0.1700

Data Index: 1404122 (Python Code)

Max Activating Token Index: 315

Text #1

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.2878. Min Act: -0.1700

Data Index: 1415090 (Python Code)

Max Activating Token Index: 782

Text #2

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.2878. Min Act: -0.1700

Data Index: 1605904 (Python Code)

Max Activating Token Index: 425

Text #3

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.2878. Min Act: -0.1700

Data Index: 1611574 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.2253. Min Act: -0.1700

Data Index: 1627974 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.2253. Min Act: -0.1700

Data Index: 1370396 (Python Code)

Max Activating Token Index: 881

Text #6

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.2253. Min Act: -0.1700

Data Index: 1447789 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1528144 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1940. Min Act: -0.1700

Data Index: 1646971 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1549898 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1398637 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.2253. Min Act: -0.1700

Data Index: 1511008 (Python Code)

Max Activating Token Index: 982

Text #12

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1581304 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1466143 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1640031 (Python Code)

Max Activating Token Index: 468

Text #15

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1315. Min Act: -0.1700

Data Index: 1624119 (Python Code)

Max Activating Token Index: 501

Text #16

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1003. Min Act: -0.1700

Data Index: 1418666 (Python Code)

Max Activating Token Index: 660

Text #17

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1628. Min Act: -0.1700

Data Index: 1412927 (Python Code)

Max Activating Token Index: 858

Text #18

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1315. Min Act: -0.1700

Data Index: 1523423 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 5.3815. Min Range: -5.3815

Max Act: 5.1315. Min Act: -0.1700

Data Index: 1362116 (Python Code)

Max Activating Token Index: 929