Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.6090. Min Act: -0.1700
Data Index: 1830302 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.4215. Min Act: -0.1700
Data Index: 7388535 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2965. Min Act: -0.1700
Data Index: 4518630 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2340. Min Act: -0.1700
Data Index: 1293516 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2340. Min Act: -0.1700
Data Index: 4834098 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.1715. Min Act: -0.1700
Data Index: 4856194 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.2028. Min Act: -0.1700
Data Index: 5811812 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.1715. Min Act: -0.1700
Data Index: 1830301 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.1715. Min Act: -0.1700
Data Index: 1082571 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.1090. Min Act: -0.1700
Data Index: 624578 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0778. Min Act: -0.1700
Data Index: 1293517 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0778. Min Act: -0.1700
Data Index: 4786479 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0465. Min Act: -0.1700
Data Index: 6680599 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0465. Min Act: -0.1700
Data Index: 4806757 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0778. Min Act: -0.1700
Data Index: 1432784 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0465. Min Act: -0.1697
Data Index: 7836398 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0465. Min Act: -0.1700
Data Index: 1562218 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0465. Min Act: -0.1700
Data Index: 2923896 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0465. Min Act: -0.1700
Data Index: 4738288 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6090. Min Range: -5.6090
Max Act: 5.0153. Min Act: -0.1700
Data Index: 5672734 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19