Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1609 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.5187. Min Range: -8.5187

Max Act: 8.5187. Min Act: -0.1700

Data Index: 1444639 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 8.5187. Min Range: -8.5187

Max Act: 8.3937. Min Act: -0.1700

Data Index: 369963 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.9562. Min Act: -0.1700

Data Index: 1574896 (Python Code)

Max Activating Token Index: 935

Text #3

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.8937. Min Act: -0.1700

Data Index: 890118 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.8937. Min Act: -0.1700

Data Index: 49625 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.8937. Min Act: -0.1700

Data Index: 1540746 (Python Code)

Max Activating Token Index: 635

Text #6

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.8937. Min Act: -0.1700

Data Index: 1597655 (Python Code)

Max Activating Token Index: 499

Text #7

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.7687. Min Act: -0.1700

Data Index: 1558092 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.8312. Min Act: -0.1700

Data Index: 971896 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.7375. Min Act: -0.1700

Data Index: 567738 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.8000. Min Act: -0.1700

Data Index: 1364743 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.8312. Min Act: -0.1700

Data Index: 438519 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.7375. Min Act: -0.1700

Data Index: 1002429 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.7062. Min Act: -0.1700

Data Index: 1509946 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.7687. Min Act: -0.1700

Data Index: 1437160 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.7375. Min Act: -0.1700

Data Index: 1575844 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.6750. Min Act: -0.1700

Data Index: 1451280 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.6750. Min Act: -0.1700

Data Index: 294970 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.7062. Min Act: -0.1700

Data Index: 1563285 (Python Code)

Max Activating Token Index: 757

Text #19

Max Range: 8.5187. Min Range: -8.5187

Max Act: 7.6750. Min Act: -0.1700

Data Index: 1556615 (Python Code)

Max Activating Token Index: 682