Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5293 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6690. Min Range: -12.6690
Max Act: 12.6690. Min Act: -0.1700
Data Index: 4483457 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6690. Min Range: -12.6690
Max Act: 12.1690. Min Act: -0.1700
Data Index: 1799807 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6690. Min Range: -12.6690
Max Act: 12.0440. Min Act: -0.1700
Data Index: 217585 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.9815. Min Act: -0.1700
Data Index: 6589581 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.9815. Min Act: -0.1699
Data Index: 7696412 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.8565. Min Act: -0.1700
Data Index: 4322810 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.7940. Min Act: -0.1700
Data Index: 2946535 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.7315. Min Act: -0.1700
Data Index: 3819433 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.7315. Min Act: -0.1700
Data Index: 6505293 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.6690. Min Act: -0.1700
Data Index: 7009576 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.6690. Min Act: -0.1700
Data Index: 285760 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.6690. Min Act: -0.1699
Data Index: 2362452 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.5440. Min Act: -0.1700
Data Index: 8427262 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.6065. Min Act: -0.1700
Data Index: 5943581 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.6065. Min Act: -0.1700
Data Index: 1027935 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.5440. Min Act: -0.1700
Data Index: 7222794 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.5440. Min Act: -0.1700
Data Index: 4193011 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.5440. Min Act: -0.1699
Data Index: 7407270 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.5440. Min Act: -0.1700
Data Index: 31254 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6690. Min Range: -12.6690
Max Act: 11.4815. Min Act: -0.1700
Data Index: 6112104 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19