Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5496 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0390. Min Range: -7.0390
Max Act: 7.0390. Min Act: -0.1700
Data Index: 6199352 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.8515. Min Act: -0.1700
Data Index: 7005130 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.8515. Min Act: -0.1700
Data Index: 2950464 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.7578. Min Act: -0.1700
Data Index: 5837450 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6953. Min Act: -0.1700
Data Index: 3115438 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6953. Min Act: -0.1700
Data Index: 3366196 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.7265. Min Act: -0.1700
Data Index: 2615558 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6953. Min Act: -0.1700
Data Index: 160500 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6640. Min Act: -0.1700
Data Index: 7548860 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6640. Min Act: -0.1700
Data Index: 8518041 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6640. Min Act: -0.1700
Data Index: 370491 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6640. Min Act: -0.1700
Data Index: 764093 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6328. Min Act: -0.1700
Data Index: 6338745 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6015. Min Act: -0.1700
Data Index: 4821698 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.6015. Min Act: -0.1700
Data Index: 4298570 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.5703. Min Act: -0.1700
Data Index: 3404160 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.5703. Min Act: -0.1700
Data Index: 2935274 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.5078. Min Act: -0.1700
Data Index: 2881343 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.5390. Min Act: -0.1700
Data Index: 3800729 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0390. Min Range: -7.0390
Max Act: 6.5390. Min Act: -0.1700
Data Index: 962900 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19