Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3615 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6001. Min Range: -7.6001
Max Act: 7.6001. Min Act: -0.1700
Data Index: 3478932 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6001. Min Range: -7.6001
Max Act: 7.2251. Min Act: -0.1700
Data Index: 510527 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6001. Min Range: -7.6001
Max Act: 7.0376. Min Act: -0.1700
Data Index: 1423511 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.9438. Min Act: -0.1700
Data Index: 7818978 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.9751. Min Act: -0.1700
Data Index: 1061313 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.9751. Min Act: -0.1700
Data Index: 1843723 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.9438. Min Act: -0.1700
Data Index: 3768569 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.9126. Min Act: -0.1700
Data Index: 7259645 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.8813. Min Act: -0.1700
Data Index: 3713216 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.8813. Min Act: -0.1700
Data Index: 4136476 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.8501. Min Act: -0.1700
Data Index: 4495882 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 7569287 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 6484363 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 8709858 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7563. Min Act: -0.1700
Data Index: 501097 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7876. Min Act: -0.1700
Data Index: 8448588 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7563. Min Act: -0.1700
Data Index: 1404869 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7251. Min Act: -0.1700
Data Index: 6963411 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7251. Min Act: -0.1700
Data Index: 7620890 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6001. Min Range: -7.6001
Max Act: 6.7251. Min Act: -0.1700
Data Index: 8140537 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19