Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5238 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1758. Min Range: -6.1758
Max Act: 6.1758. Min Act: -0.1700
Data Index: 3978749 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1758. Min Range: -6.1758
Max Act: 6.1445. Min Act: -0.1700
Data Index: 6122221 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1758. Min Range: -6.1758
Max Act: 6.0508. Min Act: -0.1699
Data Index: 4165878 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1758. Min Range: -6.1758
Max Act: 6.0508. Min Act: -0.1700
Data Index: 1115108 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.9570. Min Act: -0.1700
Data Index: 2250317 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.9258. Min Act: -0.1700
Data Index: 8062454 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8945. Min Act: -0.1699
Data Index: 3145537 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8945. Min Act: -0.1700
Data Index: 2250314 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8633. Min Act: -0.1700
Data Index: 1577212 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 5404155 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8320. Min Act: -0.1700
Data Index: 4520724 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 3145535 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 571194 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 4520717 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.8008. Min Act: -0.1700
Data Index: 7160927 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7695. Min Act: -0.1700
Data Index: 4520716 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7695. Min Act: -0.1700
Data Index: 4520722 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7695. Min Act: -0.1700
Data Index: 2018317 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7383. Min Act: -0.1700
Data Index: 3067018 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1758. Min Range: -6.1758
Max Act: 5.7383. Min Act: -0.1700
Data Index: 4520718 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19