Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5028 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.9750. Min Act: -0.1700
Data Index: 2481899 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.9750. Min Act: -0.1700
Data Index: 6435143 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.9750. Min Act: -0.1700
Data Index: 7109009 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.9125. Min Act: -0.1700
Data Index: 3453507 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.7875. Min Act: -0.1700
Data Index: 3665250 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.8500. Min Act: -0.1700
Data Index: 8008609 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.6625. Min Act: -0.1700
Data Index: 1239818 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.7250. Min Act: -0.1700
Data Index: 565014 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.6313. Min Act: -0.1700
Data Index: 3838962 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.6313. Min Act: -0.1700
Data Index: 6246846 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.6313. Min Act: -0.1700
Data Index: 6942768 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.6625. Min Act: -0.1700
Data Index: 7090341 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.6000. Min Act: -0.1700
Data Index: 3363713 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.5688. Min Act: -0.1700
Data Index: 5499714 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.5063. Min Act: -0.1700
Data Index: 2034528 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.5063. Min Act: -0.1700
Data Index: 1929592 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.5375. Min Act: -0.1700
Data Index: 1339519 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.5063. Min Act: -0.1700
Data Index: 2776970 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.5063. Min Act: -0.1700
Data Index: 84238 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9750. Min Range: -7.9750
Max Act: 7.4438. Min Act: -0.1700
Data Index: 3540853 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19