Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6009 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.7073. Min Act: -0.1700
Data Index: 7187663 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.6448. Min Act: -0.1700
Data Index: 1473295 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.5823. Min Act: -0.1700
Data Index: 7233262 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.5823. Min Act: -0.1700
Data Index: 6422575 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.5823. Min Act: -0.1700
Data Index: 1664467 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.5198. Min Act: -0.1700
Data Index: 6241447 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.5198. Min Act: -0.1700
Data Index: 543113 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.3948. Min Act: -0.1700
Data Index: 5781793 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.3323. Min Act: -0.1700
Data Index: 8702757 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.3323. Min Act: -0.1700
Data Index: 8385464 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.3323. Min Act: -0.1700
Data Index: 6203369 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.3948. Min Act: -0.1700
Data Index: 396123 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.2698. Min Act: -0.1700
Data Index: 7506838 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.2698. Min Act: -0.1700
Data Index: 7455653 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.2698. Min Act: -0.1700
Data Index: 3962162 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.2698. Min Act: -0.1700
Data Index: 2803318 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.2698. Min Act: -0.1700
Data Index: 3515236 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.3323. Min Act: -0.1700
Data Index: 747821 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.2073. Min Act: -0.1700
Data Index: 3735812 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7073. Min Range: -8.7073
Max Act: 8.2073. Min Act: -0.1700
Data Index: 3295838 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19