Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.1852. Min Act: -0.1700
Data Index: 1083639 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.0602. Min Act: -0.1700
Data Index: 4588770 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.0602. Min Act: -0.1700
Data Index: 8142005 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1852. Min Range: -6.1852
Max Act: 6.0289. Min Act: -0.1700
Data Index: 4020216 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9977. Min Act: -0.1700
Data Index: 7377483 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9664. Min Act: -0.1700
Data Index: 3175277 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9352. Min Act: -0.1700
Data Index: 5754900 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9352. Min Act: -0.1700
Data Index: 2884514 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9039. Min Act: -0.1700
Data Index: 5747614 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 7728413 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.9039. Min Act: -0.1700
Data Index: 2137459 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4624101 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 8626030 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8414. Min Act: -0.1700
Data Index: 1746353 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 1113252 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4207303 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8727. Min Act: -0.1700
Data Index: 2412932 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8414. Min Act: -0.1700
Data Index: 3721914 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.8414. Min Act: -0.1700
Data Index: 7377719 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1852. Min Range: -6.1852
Max Act: 5.7789. Min Act: -0.1700
Data Index: 2715543 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19