Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5271 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1245. Min Range: -4.1245
Max Act: 4.1245. Min Act: -0.1700
Data Index: 1466167 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.9682. Min Act: -0.1700
Data Index: 5902605 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.9369. Min Act: -0.1700
Data Index: 6316573 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.9056. Min Act: -0.1700
Data Index: 7307568 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.9056. Min Act: -0.1700
Data Index: 5485805 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.8744. Min Act: -0.1700
Data Index: 372310 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.8431. Min Act: -0.1700
Data Index: 7932336 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.8744. Min Act: -0.1700
Data Index: 6573568 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7806. Min Act: -0.1700
Data Index: 255839 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.8118. Min Act: -0.1700
Data Index: 1820820 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.8118. Min Act: -0.1700
Data Index: 5915377 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.8431. Min Act: -0.1700
Data Index: 595295 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7806. Min Act: -0.1700
Data Index: 5169500 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7806. Min Act: -0.1700
Data Index: 3131838 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7806. Min Act: -0.1700
Data Index: 255840 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7806. Min Act: -0.1700
Data Index: 4653863 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7806. Min Act: -0.1700
Data Index: 833364 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7493. Min Act: -0.1700
Data Index: 251890 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.7806. Min Act: -0.1700
Data Index: 7727619 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1245. Min Range: -4.1245
Max Act: 3.6867. Min Act: -0.1700
Data Index: 3131837 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19