Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3759 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 3504014 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 3116292 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.1992. Min Act: -0.1700
Data Index: 771360 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.1680. Min Act: -0.1700
Data Index: 5308264 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.1055. Min Act: -0.1700
Data Index: 7236632 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.1055. Min Act: -0.1700
Data Index: 6451664 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.0430. Min Act: -0.1700
Data Index: 6612623 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.0430. Min Act: -0.1700
Data Index: 4878426 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.0430. Min Act: -0.1700
Data Index: 4069477 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3242. Min Range: -6.3242
Max Act: 6.0117. Min Act: -0.1700
Data Index: 1359424 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9805. Min Act: -0.1700
Data Index: 5964103 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9805. Min Act: -0.1700
Data Index: 1538508 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9805. Min Act: -0.1700
Data Index: 4922521 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9180. Min Act: -0.1700
Data Index: 5361443 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9492. Min Act: -0.1700
Data Index: 4060819 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9492. Min Act: -0.1700
Data Index: 5283083 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9180. Min Act: -0.1700
Data Index: 1538509 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9180. Min Act: -0.1700
Data Index: 88479 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9180. Min Act: -0.1700
Data Index: 4016797 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3242. Min Range: -6.3242
Max Act: 5.9180. Min Act: -0.1700
Data Index: 2707011 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19