Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1766 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.3198. Min Act: -0.1700
Data Index: 4895846 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1948. Min Act: -0.1700
Data Index: 4509195 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.2260. Min Act: -0.1700
Data Index: 5998281 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1948. Min Act: -0.1700
Data Index: 3623792 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1948. Min Act: -0.1700
Data Index: 5739998 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1635. Min Act: -0.1700
Data Index: 7689006 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1635. Min Act: -0.1700
Data Index: 4279468 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1010. Min Act: -0.1700
Data Index: 707169 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1010. Min Act: -0.1700
Data Index: 4997096 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0698. Min Act: -0.1700
Data Index: 3819148 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0698. Min Act: -0.1700
Data Index: 5591975 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0698. Min Act: -0.1700
Data Index: 6943325 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0698. Min Act: -0.1700
Data Index: 564087 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.1010. Min Act: -0.1700
Data Index: 8421461 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0698. Min Act: -0.1700
Data Index: 1646914 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0385. Min Act: -0.1700
Data Index: 5737729 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0385. Min Act: -0.1700
Data Index: 8591411 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0073. Min Act: -0.1700
Data Index: 1952827 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3198. Min Range: -5.3198
Max Act: 5.0073. Min Act: -0.1700
Data Index: 1512213 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3198. Min Range: -5.3198
Max Act: 4.9760. Min Act: -0.1700
Data Index: 5114881 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19