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

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

Neuron 1724 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.8158. Min Act: -0.1700

Data Index: 1499349 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.8158. Min Act: -0.1700

Data Index: 1480893 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.7845. Min Act: -0.1700

Data Index: 1404300 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.7532. Min Act: -0.1700

Data Index: 1371203 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6594. Min Act: -0.1700

Data Index: 1530676 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6907. Min Act: -0.1700

Data Index: 1567238 (Python Code)

Max Activating Token Index: 868

Text #6

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1422484 (Python Code)

Max Activating Token Index: 263

Text #7

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.6594. Min Act: -0.1700

Data Index: 1390105 (Python Code)

Max Activating Token Index: 437

Text #8

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1419331 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1472470 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1598160 (Python Code)

Max Activating Token Index: 495

Text #11

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1639146 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1638737 (Python Code)

Max Activating Token Index: 248

Text #13

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1440091 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1394684 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1368057 (Python Code)

Max Activating Token Index: 522

Text #16

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1448559 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5498. Min Act: -0.1700

Data Index: 1489185 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1492007 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 3.8158. Min Range: -3.8158

Max Act: 3.5184. Min Act: -0.1700

Data Index: 1477646 (Python Code)

Max Activating Token Index: 393