Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5543 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.7558. Min Act: -0.1700
Data Index: 52226 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.7245. Min Act: -0.1700
Data Index: 515322 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.7245. Min Act: -0.1700
Data Index: 5442487 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.7245. Min Act: -0.1700
Data Index: 8118430 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.7089. Min Act: -0.1700
Data Index: 2103357 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.7245. Min Act: -0.1700
Data Index: 4339927 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6932. Min Act: -0.1700
Data Index: 4254745 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6463. Min Act: -0.1700
Data Index: 8622907 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6463. Min Act: -0.1700
Data Index: 2135589 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6306. Min Act: -0.1700
Data Index: 5025728 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6150. Min Act: -0.1700
Data Index: 2907615 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6150. Min Act: -0.1700
Data Index: 2258769 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6150. Min Act: -0.1700
Data Index: 3391219 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6150. Min Act: -0.1700
Data Index: 6597029 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.6150. Min Act: -0.1700
Data Index: 2548329 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.5837. Min Act: -0.1700
Data Index: 2307220 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.5993. Min Act: -0.1700
Data Index: 8285105 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.5837. Min Act: -0.1700
Data Index: 8626335 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.5524. Min Act: -0.1700
Data Index: 7935418 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7558. Min Range: -3.7558
Max Act: 3.5837. Min Act: -0.1700
Data Index: 4063075 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19