Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0343. Min Range: -6.0343
Max Act: 6.0343. Min Act: -0.1700
Data Index: 6869337 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.9093. Min Act: -0.1700
Data Index: 8794415 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.8468. Min Act: -0.1700
Data Index: 444935 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.7218. Min Act: -0.1700
Data Index: 2339478 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.6905. Min Act: -0.1700
Data Index: 40920 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.6905. Min Act: -0.1700
Data Index: 2339477 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.6593. Min Act: -0.1700
Data Index: 3623971 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.6905. Min Act: -0.1700
Data Index: 4918219 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.6593. Min Act: -0.1700
Data Index: 455589 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.6280. Min Act: -0.1700
Data Index: 7799901 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.6593. Min Act: -0.1700
Data Index: 8046719 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5968. Min Act: -0.1700
Data Index: 4139312 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5655. Min Act: -0.1700
Data Index: 3912503 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5655. Min Act: -0.1700
Data Index: 1856053 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5655. Min Act: -0.1700
Data Index: 7044250 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5655. Min Act: -0.1700
Data Index: 533238 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5343. Min Act: -0.1700
Data Index: 2365795 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5343. Min Act: -0.1700
Data Index: 1867404 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5343. Min Act: -0.1700
Data Index: 6730343 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0343. Min Range: -6.0343
Max Act: 5.5343. Min Act: -0.1700
Data Index: 8097864 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19