Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4093 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0789. Min Range: -6.0789
Max Act: 6.0789. Min Act: -0.1700
Data Index: 1773504 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0789. Min Range: -6.0789
Max Act: 6.0477. Min Act: -0.1700
Data Index: 1028738 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.9852. Min Act: -0.1700
Data Index: 7093280 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.9852. Min Act: -0.1700
Data Index: 8445921 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.8602. Min Act: -0.1700
Data Index: 4105898 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.8289. Min Act: -0.1700
Data Index: 3900742 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.7977. Min Act: -0.1700
Data Index: 384399 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.7977. Min Act: -0.1700
Data Index: 7446666 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.7664. Min Act: -0.1700
Data Index: 182412 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.7352. Min Act: -0.1700
Data Index: 5904796 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.7352. Min Act: -0.1700
Data Index: 7771692 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.7039. Min Act: -0.1700
Data Index: 7467336 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6727. Min Act: -0.1700
Data Index: 3614631 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6727. Min Act: -0.1700
Data Index: 2576599 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6727. Min Act: -0.1700
Data Index: 6593174 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6727. Min Act: -0.1700
Data Index: 3725906 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6414. Min Act: -0.1700
Data Index: 4074823 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6414. Min Act: -0.1700
Data Index: 4781822 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6414. Min Act: -0.1700
Data Index: 5256972 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0789. Min Range: -6.0789
Max Act: 5.6414. Min Act: -0.1700
Data Index: 7248700 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19