Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5285. Min Range: -9.5285
Max Act: 9.5285. Min Act: -0.1700
Data Index: 6018334 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5285. Min Range: -9.5285
Max Act: 9.4035. Min Act: -0.1700
Data Index: 6018328 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5285. Min Range: -9.5285
Max Act: 9.2160. Min Act: -0.1700
Data Index: 694795 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5285. Min Range: -9.5285
Max Act: 9.0910. Min Act: -0.1700
Data Index: 1253470 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.9035. Min Act: -0.1700
Data Index: 7012995 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.9035. Min Act: -0.1700
Data Index: 1918710 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.8410. Min Act: -0.1700
Data Index: 1166174 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.8410. Min Act: -0.1700
Data Index: 1017510 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.8410. Min Act: -0.1700
Data Index: 562496 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.8410. Min Act: -0.1700
Data Index: 3307327 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.8410. Min Act: -0.1700
Data Index: 2070533 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.7785. Min Act: -0.1700
Data Index: 1607784 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.7785. Min Act: -0.1700
Data Index: 1772086 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.7785. Min Act: -0.1700
Data Index: 6089933 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.7160. Min Act: -0.1700
Data Index: 1772089 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.7160. Min Act: -0.1700
Data Index: 171339 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.7785. Min Act: -0.1700
Data Index: 8077129 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.7160. Min Act: -0.1700
Data Index: 953222 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.6535. Min Act: -0.1700
Data Index: 859005 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5285. Min Range: -9.5285
Max Act: 8.6535. Min Act: -0.1700
Data Index: 3026848 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19