Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6361 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0591. Min Range: -8.0591
Max Act: 8.0591. Min Act: -0.1700
Data Index: 4507113 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.6216. Min Act: -0.1700
Data Index: 3511132 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.6841. Min Act: -0.1700
Data Index: 1874144 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.6841. Min Act: -0.1700
Data Index: 6812622 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.6216. Min Act: -0.1700
Data Index: 404139 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.6216. Min Act: -0.1700
Data Index: 5289091 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.5591. Min Act: -0.1700
Data Index: 4710674 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.5591. Min Act: -0.1700
Data Index: 7510664 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.5591. Min Act: -0.1700
Data Index: 7239449 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.5591. Min Act: -0.1700
Data Index: 6493382 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.5591. Min Act: -0.1700
Data Index: 1996852 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.5278. Min Act: -0.1700
Data Index: 8065209 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4966. Min Act: -0.1700
Data Index: 3113434 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4653. Min Act: -0.1700
Data Index: 2163818 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4341. Min Act: -0.1700
Data Index: 5568065 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4341. Min Act: -0.1700
Data Index: 7641636 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4341. Min Act: -0.1700
Data Index: 5575126 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4028. Min Act: -0.1700
Data Index: 4720503 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4028. Min Act: -0.1700
Data Index: 1430871 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0591. Min Range: -8.0591
Max Act: 7.4028. Min Act: -0.1700
Data Index: 5378158 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19