Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.4788. Min Act: -0.1700
Data Index: 2231172 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.2600. Min Act: -0.1700
Data Index: 1442496 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.2288. Min Act: -0.1700
Data Index: 7587303 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1975. Min Act: -0.1700
Data Index: 899685 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1975. Min Act: -0.1700
Data Index: 3559806 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1975. Min Act: -0.1700
Data Index: 738647 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1975. Min Act: -0.1700
Data Index: 2662906 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1663. Min Act: -0.1700
Data Index: 611501 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1350. Min Act: -0.1700
Data Index: 8174679 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1038. Min Act: -0.1700
Data Index: 8166287 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1350. Min Act: -0.1700
Data Index: 1022632 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1038. Min Act: -0.1700
Data Index: 5344691 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.1038. Min Act: -0.1700
Data Index: 1944954 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.0413. Min Act: -0.1700
Data Index: 3740930 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.0413. Min Act: -0.1700
Data Index: 4497065 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.0100. Min Act: -0.1700
Data Index: 3999323 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.0413. Min Act: -0.1700
Data Index: 5116900 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4788. Min Range: -6.4788
Max Act: 6.0100. Min Act: -0.1700
Data Index: 1904464 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4788. Min Range: -6.4788
Max Act: 5.9788. Min Act: -0.1700
Data Index: 649497 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4788. Min Range: -6.4788
Max Act: 5.9788. Min Act: -0.1700
Data Index: 5665485 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19