Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4822 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.9037. Min Act: -0.1700
Data Index: 4377226 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.9037. Min Act: -0.1700
Data Index: 6344744 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.9037. Min Act: -0.1700
Data Index: 5961028 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.9037. Min Act: -0.1700
Data Index: 4889778 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7787. Min Act: -0.1700
Data Index: 2188501 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.8412. Min Act: -0.1700
Data Index: 2700650 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.8412. Min Act: -0.1700
Data Index: 8422773 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.8412. Min Act: -0.1700
Data Index: 2643416 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.8412. Min Act: -0.1700
Data Index: 8062028 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7787. Min Act: -0.1700
Data Index: 5119008 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7787. Min Act: -0.1700
Data Index: 5822506 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7787. Min Act: -0.1700
Data Index: 7730218 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7787. Min Act: -0.1700
Data Index: 6501927 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7787. Min Act: -0.1700
Data Index: 7724710 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7162. Min Act: -0.1700
Data Index: 4519009 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7162. Min Act: -0.1700
Data Index: 2696168 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7162. Min Act: -0.1700
Data Index: 4757699 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7162. Min Act: -0.1700
Data Index: 47085 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.7162. Min Act: -0.1700
Data Index: 3428777 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9037. Min Range: -6.9037
Max Act: 6.6537. Min Act: -0.1700
Data Index: 7724709 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19