Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0714. Min Range: -6.0714
Max Act: 6.0714. Min Act: -0.1700
Data Index: 6969886 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0714. Min Range: -6.0714
Max Act: 6.0089. Min Act: -0.1700
Data Index: 2207837 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0714. Min Range: -6.0714
Max Act: 6.0089. Min Act: -0.1700
Data Index: 8677268 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0714. Min Range: -6.0714
Max Act: 6.0089. Min Act: -0.1700
Data Index: 5527161 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.8526. Min Act: -0.1700
Data Index: 7258723 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.8526. Min Act: -0.1700
Data Index: 1146272 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.8526. Min Act: -0.1700
Data Index: 5249718 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.8214. Min Act: -0.1700
Data Index: 54753 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.8214. Min Act: -0.1700
Data Index: 5479860 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.8214. Min Act: -0.1700
Data Index: 723484 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.8214. Min Act: -0.1700
Data Index: 6812843 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7589. Min Act: -0.1700
Data Index: 5853395 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7901. Min Act: -0.1700
Data Index: 6745857 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7589. Min Act: -0.1700
Data Index: 5091029 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7589. Min Act: -0.1700
Data Index: 4392679 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7276. Min Act: -0.1700
Data Index: 774844 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7589. Min Act: -0.1700
Data Index: 684540 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7589. Min Act: -0.1700
Data Index: 1909896 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7589. Min Act: -0.1700
Data Index: 622550 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0714. Min Range: -6.0714
Max Act: 5.7589. Min Act: -0.1700
Data Index: 6843112 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19