Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.8219. Min Act: -0.1700
Data Index: 5117880 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7906. Min Act: -0.1700
Data Index: 3480379 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7281. Min Act: -0.1700
Data Index: 4730074 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7281. Min Act: -0.1700
Data Index: 6132854 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7281. Min Act: -0.1700
Data Index: 6740972 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7281. Min Act: -0.1700
Data Index: 6268571 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6969. Min Act: -0.1700
Data Index: 3343767 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6969. Min Act: -0.1700
Data Index: 1452778 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6969. Min Act: -0.1700
Data Index: 122819 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.7281. Min Act: -0.1700
Data Index: 2205213 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7222684 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6969. Min Act: -0.1700
Data Index: 8158885 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6969. Min Act: -0.1700
Data Index: 4878916 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6656. Min Act: -0.1700
Data Index: 5252509 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6656. Min Act: -0.1700
Data Index: 1214055 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6229706 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7115777 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6656. Min Act: -0.1700
Data Index: 7568525 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6089121 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8219. Min Range: -6.8219
Max Act: 6.6344. Min Act: -0.1700
Data Index: 2397644 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19