Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.9065. Min Act: -0.1700
Data Index: 5980081 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.7502. Min Act: -0.1700
Data Index: 724259 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.5940. Min Act: -0.1700
Data Index: 3092992 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4690. Min Act: -0.1700
Data Index: 391711 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4690. Min Act: -0.1700
Data Index: 8311087 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 7875040 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 6108720 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 2081574 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3752. Min Act: -0.1700
Data Index: 6452216 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 3129033 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 8797932 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3440. Min Act: -0.1700
Data Index: 5082892 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3752. Min Act: -0.1700
Data Index: 6557566 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3752. Min Act: -0.1700
Data Index: 2325855 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3752. Min Act: -0.1700
Data Index: 4055823 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3752. Min Act: -0.1700
Data Index: 3299341 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3127. Min Act: -0.1700
Data Index: 753057 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.2815. Min Act: -0.1700
Data Index: 8129034 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.2815. Min Act: -0.1700
Data Index: 2219987 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.2815. Min Act: -0.1700
Data Index: 542490 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19