Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5076 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1867. Min Range: -6.1867
Max Act: 6.1867. Min Act: -0.1700
Data Index: 4903565 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1867. Min Range: -6.1867
Max Act: 6.1555. Min Act: -0.1700
Data Index: 3268519 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1867. Min Range: -6.1867
Max Act: 6.0930. Min Act: -0.1700
Data Index: 5263887 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1867. Min Range: -6.1867
Max Act: 6.0617. Min Act: -0.1700
Data Index: 814546 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1867. Min Range: -6.1867
Max Act: 6.0617. Min Act: -0.1700
Data Index: 2132384 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1867. Min Range: -6.1867
Max Act: 6.0305. Min Act: -0.1700
Data Index: 4668163 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.9680. Min Act: -0.1700
Data Index: 1485326 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.9367. Min Act: -0.1700
Data Index: 8253595 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.9055. Min Act: -0.1700
Data Index: 1019495 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.9055. Min Act: -0.1700
Data Index: 3898866 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.9055. Min Act: -0.1700
Data Index: 124593 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8742. Min Act: -0.1700
Data Index: 867577 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8742. Min Act: -0.1700
Data Index: 3363258 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8430. Min Act: -0.1700
Data Index: 4693975 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8430. Min Act: -0.1700
Data Index: 7513852 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8430. Min Act: -0.1700
Data Index: 441417 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8430. Min Act: -0.1700
Data Index: 507404 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8430. Min Act: -0.1700
Data Index: 6279987 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8430. Min Act: -0.1700
Data Index: 2591587 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1867. Min Range: -6.1867
Max Act: 5.8430. Min Act: -0.1700
Data Index: 4152127 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19