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

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

Neuron 1177 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: 5.3323. Min Range: -5.3323

Max Act: 5.3323. Min Act: -0.1700

Data Index: 594970 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.2073. Min Act: -0.1700

Data Index: 380371 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.1761. Min Act: -0.1700

Data Index: 1213073 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.2073. Min Act: -0.1700

Data Index: 850690 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0823. Min Act: -0.1700

Data Index: 849792 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.1448. Min Act: -0.1700

Data Index: 639543 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0511. Min Act: -0.1700

Data Index: 136757 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0511. Min Act: -0.1700

Data Index: 279219 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9886. Min Act: -0.1700

Data Index: 1332599 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9886. Min Act: -0.1700

Data Index: 157380 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9886. Min Act: -0.1700

Data Index: 1146438 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9261. Min Act: -0.1700

Data Index: 988054 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9573. Min Act: -0.1700

Data Index: 219883 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9261. Min Act: -0.1700

Data Index: 21359 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9261. Min Act: -0.1700

Data Index: 361180 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9573. Min Act: -0.1700

Data Index: 92017 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.8948. Min Act: -0.1700

Data Index: 1300353 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.8323. Min Act: -0.1700

Data Index: 692086 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.7386. Min Act: -0.1700

Data Index: 960228 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.7698. Min Act: -0.1700

Data Index: 89698 (C4 (Web Text))

Max Activating Token Index: 395