Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2679 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.9267. Min Act: -0.1700
Data Index: 4347507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.9267. Min Act: -0.1700
Data Index: 4675291 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.9267. Min Act: -0.1700
Data Index: 1394044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.9267. Min Act: -0.1700
Data Index: 8432317 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8954. Min Act: -0.1700
Data Index: 4484871 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8954. Min Act: -0.1700
Data Index: 4795908 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8954. Min Act: -0.1700
Data Index: 2973569 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8954. Min Act: -0.1700
Data Index: 2024159 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8954. Min Act: -0.1700
Data Index: 1913926 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 134635 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 8057299 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 6436429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 5908765 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 1958081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 5696059 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 3180755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 5581828 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 5272166 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 937856 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9267. Min Range: -3.9267
Max Act: 3.8642. Min Act: -0.1700
Data Index: 926058 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19