Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4516 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.7122. Min Act: -0.1700
Data Index: 3387468 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.5872. Min Act: -0.1700
Data Index: 4506492 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.4934. Min Act: -0.1700
Data Index: 6589513 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.4622. Min Act: -0.1700
Data Index: 3912679 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.4622. Min Act: -0.1700
Data Index: 2035788 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.3997. Min Act: -0.1700
Data Index: 4996445 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.3684. Min Act: -0.1700
Data Index: 7780951 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.3059. Min Act: -0.1700
Data Index: 4798117 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.2747. Min Act: -0.1700
Data Index: 6874685 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.2122. Min Act: -0.1700
Data Index: 1781789 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.2122. Min Act: -0.1700
Data Index: 8524865 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.1809. Min Act: -0.1700
Data Index: 6394744 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.1809. Min Act: -0.1700
Data Index: 614426 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.2122. Min Act: -0.1700
Data Index: 5319739 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.1497. Min Act: -0.1700
Data Index: 3547628 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.1497. Min Act: -0.1700
Data Index: 3275054 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.1184. Min Act: -0.1700
Data Index: 2703286 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.0872. Min Act: -0.1700
Data Index: 7289766 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.1184. Min Act: -0.1700
Data Index: 7465816 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7122. Min Range: -6.7122
Max Act: 6.0559. Min Act: -0.1700
Data Index: 3169387 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19