Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1750. Min Range: -6.1750
Max Act: 6.1750. Min Act: -0.1700
Data Index: 7168633 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1750. Min Range: -6.1750
Max Act: 6.0813. Min Act: -0.1700
Data Index: 2110619 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.9563. Min Act: -0.1700
Data Index: 5102401 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.9563. Min Act: -0.1700
Data Index: 292917 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.9563. Min Act: -0.1700
Data Index: 5015061 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.8938. Min Act: -0.1700
Data Index: 723749 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.9250. Min Act: -0.1700
Data Index: 7513456 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.8938. Min Act: -0.1700
Data Index: 4278604 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.8625. Min Act: -0.1700
Data Index: 3874464 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.8625. Min Act: -0.1700
Data Index: 5584319 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.8625. Min Act: -0.1700
Data Index: 1999478 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.8000. Min Act: -0.1700
Data Index: 6576497 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.7688. Min Act: -0.1700
Data Index: 6683916 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.7688. Min Act: -0.1700
Data Index: 623922 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.7688. Min Act: -0.1700
Data Index: 8788408 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.7688. Min Act: -0.1700
Data Index: 8025251 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.7375. Min Act: -0.1700
Data Index: 4786050 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.7688. Min Act: -0.1700
Data Index: 1221294 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.7375. Min Act: -0.1700
Data Index: 4487268 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1750. Min Range: -6.1750
Max Act: 5.6750. Min Act: -0.1700
Data Index: 1844120 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19