Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2450 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.6040. Min Act: -0.1700
Data Index: 6669222 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.1040. Min Act: -0.1700
Data Index: 1779270 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.0415. Min Act: -0.1700
Data Index: 6885573 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.0415. Min Act: -0.1700
Data Index: 6804640 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.0415. Min Act: -0.1700
Data Index: 737687 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.0415. Min Act: -0.1700
Data Index: 6940950 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.0102. Min Act: -0.1700
Data Index: 1761786 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6040. Min Range: -5.6040
Max Act: 5.0102. Min Act: -0.1700
Data Index: 6935891 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9790. Min Act: -0.1700
Data Index: 6885572 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9790. Min Act: -0.1700
Data Index: 432721 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9477. Min Act: -0.1700
Data Index: 1902861 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9477. Min Act: -0.1700
Data Index: 5422405 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9790. Min Act: -0.1700
Data Index: 737686 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9477. Min Act: -0.1700
Data Index: 2442135 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9477. Min Act: -0.1700
Data Index: 3459449 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.9165. Min Act: -0.1700
Data Index: 7666450 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.8852. Min Act: -0.1700
Data Index: 1333051 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.8852. Min Act: -0.1700
Data Index: 5638767 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.8852. Min Act: -0.1700
Data Index: 6702026 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6040. Min Range: -5.6040
Max Act: 4.8852. Min Act: -0.1700
Data Index: 2150704 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19