Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2588 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0524. Min Range: -9.0524
Max Act: 9.0524. Min Act: -0.1700
Data Index: 5375382 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.7399. Min Act: -0.1700
Data Index: 4382502 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.6774. Min Act: -0.1700
Data Index: 5450228 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.5524. Min Act: -0.1700
Data Index: 3633091 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.4899. Min Act: -0.1700
Data Index: 8256896 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.3649. Min Act: -0.1700
Data Index: 2665617 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.3649. Min Act: -0.1700
Data Index: 4983317 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.3649. Min Act: -0.1700
Data Index: 3750962 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.2087. Min Act: -0.1700
Data Index: 5890784 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.2087. Min Act: -0.1700
Data Index: 1271903 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.2399. Min Act: -0.1700
Data Index: 5769542 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.2087. Min Act: -0.1700
Data Index: 6536033 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.1149. Min Act: -0.1700
Data Index: 3257094 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.0837. Min Act: -0.1700
Data Index: 210992 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.0524. Min Act: -0.1700
Data Index: 8812906 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.0524. Min Act: -0.1700
Data Index: 4480739 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0524. Min Range: -9.0524
Max Act: 7.9899. Min Act: -0.1700
Data Index: 2375851 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0524. Min Range: -9.0524
Max Act: 8.0212. Min Act: -0.1700
Data Index: 8063608 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0524. Min Range: -9.0524
Max Act: 7.9899. Min Act: -0.1700
Data Index: 5516040 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0524. Min Range: -9.0524
Max Act: 7.9899. Min Act: -0.1700
Data Index: 8256895 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19