Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.9167. Min Act: -0.1700
Data Index: 6071577 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.8229. Min Act: -0.1700
Data Index: 4342549 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.7917. Min Act: -0.1700
Data Index: 2256042 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.8229. Min Act: -0.1700
Data Index: 4510301 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.7604. Min Act: -0.1700
Data Index: 1803077 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.7604. Min Act: -0.1700
Data Index: 8066903 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.7292. Min Act: -0.1700
Data Index: 773105 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.7292. Min Act: -0.1700
Data Index: 5106764 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6979. Min Act: -0.1700
Data Index: 2045149 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6979. Min Act: -0.1700
Data Index: 4730901 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6979. Min Act: -0.1700
Data Index: 2760881 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6979. Min Act: -0.1700
Data Index: 7133661 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6667. Min Act: -0.1700
Data Index: 5815787 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6354. Min Act: -0.1700
Data Index: 8746545 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6042. Min Act: -0.1700
Data Index: 5901997 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6354. Min Act: -0.1700
Data Index: 2433598 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6354. Min Act: -0.1700
Data Index: 5837196 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6354. Min Act: -0.1700
Data Index: 7700811 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6667. Min Act: -0.1700
Data Index: 6036721 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9167. Min Range: -4.9167
Max Act: 4.6354. Min Act: -0.1700
Data Index: 3287873 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19