Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3923 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0807. Min Range: -7.0807
Max Act: 7.0807. Min Act: -0.1700
Data Index: 6720804 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0807. Min Range: -7.0807
Max Act: 7.0182. Min Act: -0.1700
Data Index: 3786850 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.8932. Min Act: -0.1700
Data Index: 2160714 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.8620. Min Act: -0.1700
Data Index: 8217061 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.7995. Min Act: -0.1700
Data Index: 4127581 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.7682. Min Act: -0.1700
Data Index: 3292886 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.7057. Min Act: -0.1700
Data Index: 3641224 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.7057. Min Act: -0.1700
Data Index: 7486675 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.6432. Min Act: -0.1700
Data Index: 6951341 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.6120. Min Act: -0.1700
Data Index: 708166 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.6120. Min Act: -0.1700
Data Index: 92341 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.5807. Min Act: -0.1700
Data Index: 146763 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.5495. Min Act: -0.1700
Data Index: 5122124 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.5807. Min Act: -0.1700
Data Index: 7692537 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.5182. Min Act: -0.1700
Data Index: 5100759 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.4870. Min Act: -0.1700
Data Index: 4175012 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.4870. Min Act: -0.1700
Data Index: 6935184 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.4557. Min Act: -0.1700
Data Index: 6402666 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.4557. Min Act: -0.1700
Data Index: 2757873 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0807. Min Range: -7.0807
Max Act: 6.4557. Min Act: -0.1700
Data Index: 3001085 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19