Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.2517. Min Act: -0.1700
Data Index: 5514437 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.1888. Min Act: -0.1700
Data Index: 4506200 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.1573. Min Act: -0.1700
Data Index: 8246672 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.1573. Min Act: -0.1700
Data Index: 3084643 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.1416. Min Act: -0.1700
Data Index: 3607333 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.1888. Min Act: -0.1700
Data Index: 5840933 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.1258. Min Act: -0.1700
Data Index: 2251273 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.0786. Min Act: -0.1700
Data Index: 1429834 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.0470. Min Act: -0.1700
Data Index: 8190807 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.0470. Min Act: -0.1700
Data Index: 6052686 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.9996. Min Act: -0.1700
Data Index: 7945504 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2517. Min Range: -3.2517
Max Act: 3.0154. Min Act: -0.1700
Data Index: 8095609 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.9838. Min Act: -0.1700
Data Index: 7258851 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.9363. Min Act: -0.1700
Data Index: 58390 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.8888. Min Act: -0.1700
Data Index: 6647283 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.9522. Min Act: -0.1700
Data Index: 3616938 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.9205. Min Act: -0.1700
Data Index: 7733922 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.8888. Min Act: -0.1700
Data Index: 8354253 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.9046. Min Act: -0.1700
Data Index: 8784007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2517. Min Range: -3.2517
Max Act: 2.8888. Min Act: -0.1700
Data Index: 1275170 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19