Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4152 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0558. Min Range: -1.0558
Max Act: 1.0558. Min Act: -0.1700
Data Index: 8557451 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0558. Min Range: -1.0558
Max Act: 1.0383. Min Act: -0.1700
Data Index: 3601179 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0558. Min Range: -1.0558
Max Act: 1.0296. Min Act: -0.1700
Data Index: 6690517 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0558. Min Range: -1.0558
Max Act: 1.0209. Min Act: -0.1700
Data Index: 2457284 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0558. Min Range: -1.0558
Max Act: 1.0036. Min Act: -0.1700
Data Index: 560131 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9862. Min Act: -0.1700
Data Index: 4052320 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9862. Min Act: -0.1700
Data Index: 4689691 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0558. Min Range: -1.0558
Max Act: 1.0036. Min Act: -0.1700
Data Index: 4696409 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9862. Min Act: -0.1700
Data Index: 5832301 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9776. Min Act: -0.1700
Data Index: 4182548 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9862. Min Act: -0.1700
Data Index: 3619773 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9862. Min Act: -0.1700
Data Index: 6164387 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9862. Min Act: -0.1700
Data Index: 684699 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9862. Min Act: -0.1700
Data Index: 3553135 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9776. Min Act: -0.1700
Data Index: 1234431 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9689. Min Act: -0.1700
Data Index: 8088695 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9689. Min Act: -0.1700
Data Index: 7607696 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9689. Min Act: -0.1700
Data Index: 7559237 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9689. Min Act: -0.1700
Data Index: 4910262 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0558. Min Range: -1.0558
Max Act: 0.9776. Min Act: -0.1700
Data Index: 3250500 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19