Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9125. Min Range: -7.9125
Max Act: 7.9125. Min Act: -0.1700
Data Index: 1925703 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9125. Min Range: -7.9125
Max Act: 7.2250. Min Act: -0.1700
Data Index: 2872528 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9125. Min Range: -7.9125
Max Act: 7.1625. Min Act: -0.1700
Data Index: 2792550 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9125. Min Range: -7.9125
Max Act: 7.0688. Min Act: -0.1700
Data Index: 6422128 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9125. Min Range: -7.9125
Max Act: 7.0375. Min Act: -0.1700
Data Index: 5199805 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9125. Min Range: -7.9125
Max Act: 7.0375. Min Act: -0.1700
Data Index: 2428887 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.9750. Min Act: -0.1700
Data Index: 7065665 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.9438. Min Act: -0.1700
Data Index: 2174185 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.8500. Min Act: -0.1700
Data Index: 5781507 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.8813. Min Act: -0.1700
Data Index: 1197189 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.8500. Min Act: -0.1700
Data Index: 1381025 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.7875. Min Act: -0.1700
Data Index: 7254133 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.7563. Min Act: -0.1700
Data Index: 156134 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.7563. Min Act: -0.1700
Data Index: 5416169 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.7563. Min Act: -0.1700
Data Index: 3065371 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 457025 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 6839453 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.6938. Min Act: -0.1700
Data Index: 5703739 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.6938. Min Act: -0.1700
Data Index: 896233 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9125. Min Range: -7.9125
Max Act: 6.6938. Min Act: -0.1700
Data Index: 3778312 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19