Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.3750. Min Act: -0.1700
Data Index: 5620594 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.2500. Min Act: -0.1700
Data Index: 2930029 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.2813. Min Act: -0.1700
Data Index: 6222858 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1875. Min Act: -0.1700
Data Index: 5769591 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1563. Min Act: -0.1700
Data Index: 8470454 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1563. Min Act: -0.1700
Data Index: 2352189 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1563. Min Act: -0.1700
Data Index: 266529 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1250. Min Act: -0.1700
Data Index: 4738539 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1563. Min Act: -0.1700
Data Index: 8519930 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1250. Min Act: -0.1700
Data Index: 294583 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.1250. Min Act: -0.1700
Data Index: 1278982 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0625. Min Act: -0.1700
Data Index: 2147942 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0938. Min Act: -0.1700
Data Index: 6677966 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0938. Min Act: -0.1700
Data Index: 5337105 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0625. Min Act: -0.1700
Data Index: 3841890 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0625. Min Act: -0.1700
Data Index: 745108 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0313. Min Act: -0.1700
Data Index: 4655634 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0313. Min Act: -0.1700
Data Index: 2930034 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0625. Min Act: -0.1700
Data Index: 5335443 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3750. Min Range: -5.3750
Max Act: 5.0313. Min Act: -0.1700
Data Index: 6338759 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19