Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1324 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.1899. Min Act: -0.1700
Data Index: 5317132 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.1274. Min Act: -0.1700
Data Index: 3409560 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0649. Min Act: -0.1700
Data Index: 5129518 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0649. Min Act: -0.1700
Data Index: 8054794 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0336. Min Act: -0.1700
Data Index: 7789551 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0649. Min Act: -0.1700
Data Index: 92898 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0023. Min Act: -0.1700
Data Index: 92897 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0023. Min Act: -0.1700
Data Index: 1189749 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0023. Min Act: -0.1700
Data Index: 188670 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1899. Min Range: -4.1899
Max Act: 4.0023. Min Act: -0.1700
Data Index: 7631381 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9711. Min Act: -0.1700
Data Index: 3603565 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9711. Min Act: -0.1700
Data Index: 4999609 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9711. Min Act: -0.1700
Data Index: 960691 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9398. Min Act: -0.1700
Data Index: 6760702 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9398. Min Act: -0.1700
Data Index: 7063320 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9398. Min Act: -0.1700
Data Index: 3448590 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9711. Min Act: -0.1700
Data Index: 4086559 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9398. Min Act: -0.1700
Data Index: 4370668 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9398. Min Act: -0.1700
Data Index: 4710681 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1899. Min Range: -4.1899
Max Act: 3.9398. Min Act: -0.1700
Data Index: 6296544 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19