Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5822 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.7681. Min Act: -0.1700
Data Index: 6706933 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.7056. Min Act: -0.1700
Data Index: 4646464 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.4556. Min Act: -0.1700
Data Index: 2008212 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.2994. Min Act: -0.1700
Data Index: 6986689 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.2681. Min Act: -0.1700
Data Index: 7438403 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.2056. Min Act: -0.1700
Data Index: 1260615 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.1119. Min Act: -0.1700
Data Index: 5644000 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.1119. Min Act: -0.1700
Data Index: 8613497 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.0806. Min Act: -0.1700
Data Index: 7306522 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.0494. Min Act: -0.1700
Data Index: 1395409 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.0806. Min Act: -0.1700
Data Index: 5779808 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.0806. Min Act: -0.1700
Data Index: 8753272 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7681. Min Range: -8.7681
Max Act: 8.0494. Min Act: -0.1700
Data Index: 2435743 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7681. Min Range: -8.7681
Max Act: 7.9869. Min Act: -0.1700
Data Index: 7852765 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7681. Min Range: -8.7681
Max Act: 7.9869. Min Act: -0.1700
Data Index: 5291119 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7681. Min Range: -8.7681
Max Act: 7.9244. Min Act: -0.1700
Data Index: 6985062 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7681. Min Range: -8.7681
Max Act: 7.9869. Min Act: -0.1700
Data Index: 2901481 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7681. Min Range: -8.7681
Max Act: 7.9244. Min Act: -0.1700
Data Index: 150527 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7681. Min Range: -8.7681
Max Act: 7.9244. Min Act: -0.1700
Data Index: 5690225 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7681. Min Range: -8.7681
Max Act: 7.8931. Min Act: -0.1700
Data Index: 836918 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19