Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5853 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3707. Min Range: -6.3707
Max Act: 6.3707. Min Act: -0.1700
Data Index: 1643843 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.8082. Min Act: -0.1700
Data Index: 4826400 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.6207. Min Act: -0.1700
Data Index: 2734012 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.6207. Min Act: -0.1700
Data Index: 5196447 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.6207. Min Act: -0.1700
Data Index: 6901231 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.5269. Min Act: -0.1700
Data Index: 8308218 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.5269. Min Act: -0.1700
Data Index: 2162433 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.4644. Min Act: -0.1700
Data Index: 1119379 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5484959 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.4332. Min Act: -0.1700
Data Index: 7381318 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.4332. Min Act: -0.1700
Data Index: 7929653 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.4019. Min Act: -0.1700
Data Index: 1342886 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.4332. Min Act: -0.1700
Data Index: 6721290 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.4019. Min Act: -0.1700
Data Index: 3509927 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.3707. Min Act: -0.1700
Data Index: 2601053 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.3707. Min Act: -0.1700
Data Index: 4237170 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.3707. Min Act: -0.1700
Data Index: 6814958 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.3707. Min Act: -0.1700
Data Index: 3678580 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.3707. Min Act: -0.1700
Data Index: 3038393 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3707. Min Range: -6.3707
Max Act: 5.3082. Min Act: -0.1700
Data Index: 5604903 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19