Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3867 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0598. Min Range: -5.0598
Max Act: 5.0598. Min Act: -0.1700
Data Index: 5440599 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0598. Min Range: -5.0598
Max Act: 5.0285. Min Act: -0.1700
Data Index: 2575478 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.9973. Min Act: -0.1700
Data Index: 6834083 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8723. Min Act: -0.1700
Data Index: 3035625 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8723. Min Act: -0.1700
Data Index: 5014407 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8410. Min Act: -0.1700
Data Index: 4965779 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8410. Min Act: -0.1700
Data Index: 1742971 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8098. Min Act: -0.1700
Data Index: 10990 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8098. Min Act: -0.1700
Data Index: 1463273 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8098. Min Act: -0.1700
Data Index: 8695517 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.8098. Min Act: -0.1700
Data Index: 7369685 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7785. Min Act: -0.1700
Data Index: 3689581 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7473. Min Act: -0.1700
Data Index: 3693270 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7473. Min Act: -0.1700
Data Index: 2966629 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7473. Min Act: -0.1700
Data Index: 143502 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7473. Min Act: -0.1700
Data Index: 8507121 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7473. Min Act: -0.1700
Data Index: 2509109 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7160. Min Act: -0.1700
Data Index: 1413812 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7160. Min Act: -0.1700
Data Index: 1961573 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0598. Min Range: -5.0598
Max Act: 4.7160. Min Act: -0.1700
Data Index: 1051552 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19