Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0539. Min Range: -6.0539
Max Act: 6.0539. Min Act: -0.1700
Data Index: 8391081 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0539. Min Range: -6.0539
Max Act: 6.0226. Min Act: -0.1700
Data Index: 5767644 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.9289. Min Act: -0.1700
Data Index: 3178146 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.9289. Min Act: -0.1700
Data Index: 3300883 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.9289. Min Act: -0.1700
Data Index: 164192 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.8976. Min Act: -0.1700
Data Index: 7165071 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.8976. Min Act: -0.1700
Data Index: 1872391 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.8039. Min Act: -0.1700
Data Index: 1704838 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.7726. Min Act: -0.1700
Data Index: 7876663 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.8039. Min Act: -0.1700
Data Index: 6678751 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.7414. Min Act: -0.1700
Data Index: 5331900 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.7414. Min Act: -0.1700
Data Index: 1074841 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.7414. Min Act: -0.1700
Data Index: 4578164 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.6789. Min Act: -0.1700
Data Index: 141931 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.6789. Min Act: -0.1700
Data Index: 2461060 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.6476. Min Act: -0.1700
Data Index: 7504306 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.6164. Min Act: -0.1700
Data Index: 847198 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.5851. Min Act: -0.1700
Data Index: 299649 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.6164. Min Act: -0.1700
Data Index: 8742281 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0539. Min Range: -6.0539
Max Act: 5.6164. Min Act: -0.1700
Data Index: 2164520 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19