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

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

Neuron 55 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: 3.5634. Min Range: -3.5634

Max Act: 3.5634. Min Act: -0.1700

Data Index: 1634895 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3753. Min Act: -0.1700

Data Index: 1610882 (Python Code)

Max Activating Token Index: 709

Text #2

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1481766 (Python Code)

Max Activating Token Index: 243

Text #3

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3596. Min Act: -0.1700

Data Index: 1641872 (Python Code)

Max Activating Token Index: 341

Text #4

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3753. Min Act: -0.1700

Data Index: 1481613 (Python Code)

Max Activating Token Index: 845

Text #5

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1627469 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3439. Min Act: -0.1700

Data Index: 1496605 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3439. Min Act: -0.1700

Data Index: 1558720 (Python Code)

Max Activating Token Index: 803

Text #8

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3596. Min Act: -0.1700

Data Index: 389061 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3439. Min Act: -0.1700

Data Index: 1524388 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1469430 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1537802 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1397472 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.2968. Min Act: -0.1700

Data Index: 1526945 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.2654. Min Act: -0.1700

Data Index: 1526745 (Python Code)

Max Activating Token Index: 661

Text #15

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1643781 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.3282. Min Act: -0.1700

Data Index: 1410162 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.2654. Min Act: -0.1700

Data Index: 1613802 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.2811. Min Act: -0.1700

Data Index: 1562889 (Python Code)

Max Activating Token Index: 894

Text #19

Max Range: 3.5634. Min Range: -3.5634

Max Act: 3.2497. Min Act: -0.1700

Data Index: 1365884 (Python Code)

Max Activating Token Index: 234