Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5493 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8222. Min Range: -8.8222
Max Act: 8.8222. Min Act: -0.1700
Data Index: 2488684 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8222. Min Range: -8.8222
Max Act: 8.1972. Min Act: -0.1700
Data Index: 2210019 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8222. Min Range: -8.8222
Max Act: 7.9785. Min Act: -0.1700
Data Index: 5963923 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8222. Min Range: -8.8222
Max Act: 7.5097. Min Act: -0.1700
Data Index: 1015634 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8222. Min Range: -8.8222
Max Act: 7.3222. Min Act: -0.1700
Data Index: 6144885 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8222. Min Range: -8.8222
Max Act: 7.2910. Min Act: -0.1700
Data Index: 5688726 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8222. Min Range: -8.8222
Max Act: 7.1972. Min Act: -0.1700
Data Index: 6191723 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8222. Min Range: -8.8222
Max Act: 7.1035. Min Act: -0.1700
Data Index: 1067592 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.9472. Min Act: -0.1700
Data Index: 3828724 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.9785. Min Act: -0.1700
Data Index: 4098382 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.8222. Min Act: -0.1700
Data Index: 5060740 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.7910. Min Act: -0.1700
Data Index: 7280890 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.7910. Min Act: -0.1700
Data Index: 1976695 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.7597. Min Act: -0.1700
Data Index: 1976696 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.7597. Min Act: -0.1700
Data Index: 6015551 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.6660. Min Act: -0.1700
Data Index: 7661571 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.6660. Min Act: -0.1700
Data Index: 5828834 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.5722. Min Act: -0.1700
Data Index: 4168299 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.5410. Min Act: -0.1700
Data Index: 3145293 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8222. Min Range: -8.8222
Max Act: 6.5410. Min Act: -0.1700
Data Index: 3411345 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19