Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 368 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.9219. Min Act: -0.1700

Data Index: 426442 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.8609. Min Act: -0.1700

Data Index: 280101 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.8047. Min Act: -0.1700

Data Index: 796700 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.8036. Min Act: -0.1700

Data Index: 21253 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.7650. Min Act: -0.1700

Data Index: 14380 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.7417. Min Act: -0.1700

Data Index: 171817 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.7429. Min Act: -0.1700

Data Index: 423889 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.7023. Min Act: -0.1700

Data Index: 358515 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.7244. Min Act: -0.1700

Data Index: 632998 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.7037. Min Act: -0.1700

Data Index: 667794 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6906. Min Act: -0.1700

Data Index: 1275934 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6712. Min Act: -0.1700

Data Index: 1251917 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6812. Min Act: -0.1700

Data Index: 755178 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6863. Min Act: -0.1700

Data Index: 1106239 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6696. Min Act: -0.1700

Data Index: 49605 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6933. Min Act: -0.1700

Data Index: 468309 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6698. Min Act: -0.1700

Data Index: 679344 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6689. Min Act: -0.1700

Data Index: 1104999 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6482. Min Act: -0.1700

Data Index: 558372 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 3.9219. Min Range: -3.9219

Max Act: 3.6512. Min Act: -0.1700

Data Index: 913426 (C4 (Web Text))

Max Activating Token Index: 729