Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5016 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.9028. Min Act: -0.1700
Data Index: 3630655 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.5278. Min Act: -0.1700
Data Index: 899915 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.3090. Min Act: -0.1700
Data Index: 4560007 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.3090. Min Act: -0.1700
Data Index: 2414217 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.2778. Min Act: -0.1700
Data Index: 6920447 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.2465. Min Act: -0.1700
Data Index: 29201 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.2153. Min Act: -0.1700
Data Index: 7456673 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.1528. Min Act: -0.1700
Data Index: 4536921 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.1528. Min Act: -0.1700
Data Index: 3504113 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.1215. Min Act: -0.1700
Data Index: 8018996 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.0903. Min Act: -0.1700
Data Index: 1635602 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.0590. Min Act: -0.1700
Data Index: 6992636 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.0590. Min Act: -0.1700
Data Index: 4202937 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.0278. Min Act: -0.1700
Data Index: 262731 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.0278. Min Act: -0.1700
Data Index: 2326261 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.0278. Min Act: -0.1700
Data Index: 1489919 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9028. Min Range: -5.9028
Max Act: 4.9965. Min Act: -0.1700
Data Index: 935151 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9028. Min Range: -5.9028
Max Act: 4.9965. Min Act: -0.1700
Data Index: 262730 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9028. Min Range: -5.9028
Max Act: 4.9965. Min Act: -0.1700
Data Index: 6787741 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9028. Min Range: -5.9028
Max Act: 5.0278. Min Act: -0.1700
Data Index: 1007495 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19