Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.6885. Min Act: -0.1700
Data Index: 5432894 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.4698. Min Act: -0.1700
Data Index: 7527225 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.3135. Min Act: -0.1700
Data Index: 8039576 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.3135. Min Act: -0.1699
Data Index: 5392379 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.3135. Min Act: -0.1700
Data Index: 1590861 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.1885. Min Act: -0.1700
Data Index: 3746082 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.2198. Min Act: -0.1700
Data Index: 6532678 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.1885. Min Act: -0.1700
Data Index: 756432 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.1260. Min Act: -0.1700
Data Index: 7662802 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.1260. Min Act: -0.1700
Data Index: 4633777 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.1260. Min Act: -0.1700
Data Index: 885456 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.1260. Min Act: -0.1700
Data Index: 2795397 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.0948. Min Act: -0.1700
Data Index: 520684 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.0323. Min Act: -0.1700
Data Index: 8628304 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.0323. Min Act: -0.1700
Data Index: 7735366 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.0010. Min Act: -0.1700
Data Index: 3206338 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.0323. Min Act: -0.1700
Data Index: 6864875 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.0010. Min Act: -0.1700
Data Index: 5392377 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6885. Min Range: -6.6885
Max Act: 6.0010. Min Act: -0.1700
Data Index: 101054 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6885. Min Range: -6.6885
Max Act: 5.9698. Min Act: -0.1700
Data Index: 4034658 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19