Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.9620. Min Act: -0.1700
Data Index: 2849979 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.6808. Min Act: -0.1700
Data Index: 5949601 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.5870. Min Act: -0.1700
Data Index: 4216028 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.5558. Min Act: -0.1700
Data Index: 5091950 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.4933. Min Act: -0.1700
Data Index: 4262481 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.4620. Min Act: -0.1700
Data Index: 4272818 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.4620. Min Act: -0.1700
Data Index: 5631219 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.4620. Min Act: -0.1700
Data Index: 2172219 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3995. Min Act: -0.1700
Data Index: 5674764 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.4308. Min Act: -0.1700
Data Index: 2944576 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3683. Min Act: -0.1700
Data Index: 3047554 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3683. Min Act: -0.1700
Data Index: 6069160 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3683. Min Act: -0.1700
Data Index: 7104639 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3683. Min Act: -0.1700
Data Index: 21937 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3683. Min Act: -0.1700
Data Index: 8619763 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3370. Min Act: -0.1700
Data Index: 1426463 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3058. Min Act: -0.1700
Data Index: 3452328 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3370. Min Act: -0.1700
Data Index: 7616311 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3370. Min Act: -0.1700
Data Index: 5048952 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.3370. Min Act: -0.1700
Data Index: 2619373 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19