Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1965 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.6926. Min Act: -0.1700
Data Index: 4440013 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.6301. Min Act: -0.1700
Data Index: 4575448 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5988. Min Act: -0.1700
Data Index: 6304151 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5676. Min Act: -0.1700
Data Index: 7342528 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 6636701 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1699
Data Index: 3822146 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 5920033 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 6123 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 5795413 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 6898251 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 437543 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5051. Min Act: -0.1700
Data Index: 2386577 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 3484127 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5051. Min Act: -0.1700
Data Index: 5998383 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5051. Min Act: -0.1700
Data Index: 2406008 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5363. Min Act: -0.1700
Data Index: 342653 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5051. Min Act: -0.1700
Data Index: 1869639 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5051. Min Act: -0.1700
Data Index: 3868938 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.4738. Min Act: -0.1700
Data Index: 6563179 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6926. Min Range: -5.6926
Max Act: 5.5051. Min Act: -0.1700
Data Index: 4348066 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19