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

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

Neuron 1826 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: 5.4893. Min Range: -5.4893

Max Act: 5.4893. Min Act: -0.1700

Data Index: 1420272 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.3018. Min Act: -0.1700

Data Index: 1613864 (Python Code)

Max Activating Token Index: 381

Text #2

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.3956. Min Act: -0.1700

Data Index: 1651404 (Python Code)

Max Activating Token Index: 868

Text #3

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.3331. Min Act: -0.1700

Data Index: 1499601 (Python Code)

Max Activating Token Index: 170

Text #4

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.2393. Min Act: -0.1700

Data Index: 1537760 (Python Code)

Max Activating Token Index: 341

Text #5

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1768. Min Act: -0.1700

Data Index: 1598663 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.2706. Min Act: -0.1700

Data Index: 1482918 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.2081. Min Act: -0.1700

Data Index: 1516025 (Python Code)

Max Activating Token Index: 595

Text #8

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.2393. Min Act: -0.1700

Data Index: 1545521 (Python Code)

Max Activating Token Index: 795

Text #9

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.2081. Min Act: -0.1700

Data Index: 1601380 (Python Code)

Max Activating Token Index: 847

Text #10

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1456. Min Act: -0.1700

Data Index: 1447560 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1768. Min Act: -0.1700

Data Index: 956443 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1456. Min Act: -0.1700

Data Index: 1472185 (Python Code)

Max Activating Token Index: 996

Text #13

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.0831. Min Act: -0.1700

Data Index: 1382851 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1143. Min Act: -0.1700

Data Index: 1624109 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1768. Min Act: -0.1700

Data Index: 1449561 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1768. Min Act: -0.1700

Data Index: 1419853 (Python Code)

Max Activating Token Index: 776

Text #17

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1768. Min Act: -0.1700

Data Index: 1398640 (Python Code)

Max Activating Token Index: 955

Text #18

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1143. Min Act: -0.1700

Data Index: 1479073 (Python Code)

Max Activating Token Index: 996

Text #19

Max Range: 5.4893. Min Range: -5.4893

Max Act: 5.1143. Min Act: -0.1700

Data Index: 1414759 (Python Code)

Max Activating Token Index: 991