Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1979 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1471. Min Range: -7.1471
Max Act: 7.1471. Min Act: -0.1700
Data Index: 7830837 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.9596. Min Act: -0.1700
Data Index: 6522778 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.9596. Min Act: -0.1700
Data Index: 5590628 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.9596. Min Act: -0.1700
Data Index: 7396181 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.9284. Min Act: -0.1700
Data Index: 5729457 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.9284. Min Act: -0.1700
Data Index: 1683989 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.9284. Min Act: -0.1700
Data Index: 7711681 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8971. Min Act: -0.1700
Data Index: 6795970 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8971. Min Act: -0.1700
Data Index: 231876 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8971. Min Act: -0.1700
Data Index: 5358555 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8659. Min Act: -0.1700
Data Index: 3541211 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8659. Min Act: -0.1700
Data Index: 1946324 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8034. Min Act: -0.1700
Data Index: 3346740 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8346. Min Act: -0.1700
Data Index: 8146585 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8034. Min Act: -0.1700
Data Index: 6260830 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8346. Min Act: -0.1700
Data Index: 4907282 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8034. Min Act: -0.1700
Data Index: 6451083 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8034. Min Act: -0.1700
Data Index: 3640906 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8034. Min Act: -0.1700
Data Index: 6484758 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1471. Min Range: -7.1471
Max Act: 6.8034. Min Act: -0.1700
Data Index: 6511859 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19