Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2438. Min Range: -6.2438
Max Act: 6.2438. Min Act: -0.1700
Data Index: 6682055 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2438. Min Range: -6.2438
Max Act: 6.1501. Min Act: -0.1700
Data Index: 8018419 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.8376. Min Act: -0.1700
Data Index: 311279 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.7126. Min Act: -0.1700
Data Index: 2701689 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.7126. Min Act: -0.1700
Data Index: 7734795 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.6813. Min Act: -0.1700
Data Index: 1112009 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.6188. Min Act: -0.1700
Data Index: 2723402 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5876. Min Act: -0.1700
Data Index: 2189386 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5876. Min Act: -0.1700
Data Index: 7230574 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5876. Min Act: -0.1700
Data Index: 164663 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5876. Min Act: -0.1700
Data Index: 39506 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5563. Min Act: -0.1700
Data Index: 7868779 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5251. Min Act: -0.1700
Data Index: 7446720 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5563. Min Act: -0.1700
Data Index: 7808317 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5563. Min Act: -0.1700
Data Index: 313644 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5563. Min Act: -0.1700
Data Index: 5151713 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5563. Min Act: -0.1700
Data Index: 8188675 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5563. Min Act: -0.1700
Data Index: 369141 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.5251. Min Act: -0.1700
Data Index: 4337116 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2438. Min Range: -6.2438
Max Act: 5.4938. Min Act: -0.1700
Data Index: 2701842 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19