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

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

Neuron 1010 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.8608. Min Act: -0.1700

Data Index: 1362539 (Python Code)

Max Activating Token Index: 209

Text #1

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.6418. Min Act: -0.1700

Data Index: 1507507 (Python Code)

Max Activating Token Index: 798

Text #2

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.6731. Min Act: -0.1700

Data Index: 1555147 (Python Code)

Max Activating Token Index: 984

Text #3

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.6418. Min Act: -0.1700

Data Index: 1413938 (Python Code)

Max Activating Token Index: 628

Text #4

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.6105. Min Act: -0.1700

Data Index: 1460098 (Python Code)

Max Activating Token Index: 978

Text #5

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.6418. Min Act: -0.1700

Data Index: 1420604 (Python Code)

Max Activating Token Index: 423

Text #6

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5792. Min Act: -0.1700

Data Index: 1534722 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5792. Min Act: -0.1700

Data Index: 1488705 (Python Code)

Max Activating Token Index: 66

Text #8

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5792. Min Act: -0.1700

Data Index: 1607198 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5478. Min Act: -0.1700

Data Index: 1474988 (Python Code)

Max Activating Token Index: 106

Text #10

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5478. Min Act: -0.1700

Data Index: 1453405 (Python Code)

Max Activating Token Index: 903

Text #11

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5792. Min Act: -0.1700

Data Index: 1530457 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5792. Min Act: -0.1700

Data Index: 1436247 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5792. Min Act: -0.1700

Data Index: 1619299 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5478. Min Act: -0.1700

Data Index: 1391373 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5478. Min Act: -0.1700

Data Index: 1590093 (Python Code)

Max Activating Token Index: 288

Text #16

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5478. Min Act: -0.1700

Data Index: 1553693 (Python Code)

Max Activating Token Index: 759

Text #17

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.4852. Min Act: -0.1700

Data Index: 1402346 (Python Code)

Max Activating Token Index: 31

Text #18

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.4852. Min Act: -0.1700

Data Index: 1529430 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 3.8608. Min Range: -3.8608

Max Act: 3.5478. Min Act: -0.1700

Data Index: 1539735 (Python Code)

Max Activating Token Index: 94