Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3767 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2996. Min Range: -9.2996
Max Act: 9.2996. Min Act: -0.1700
Data Index: 7670226 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2996. Min Range: -9.2996
Max Act: 9.2371. Min Act: -0.1700
Data Index: 2898611 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2996. Min Range: -9.2996
Max Act: 9.1746. Min Act: -0.1700
Data Index: 5944895 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2996. Min Range: -9.2996
Max Act: 9.1746. Min Act: -0.1700
Data Index: 5224990 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2996. Min Range: -9.2996
Max Act: 9.1746. Min Act: -0.1700
Data Index: 7912695 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2996. Min Range: -9.2996
Max Act: 9.1121. Min Act: -0.1700
Data Index: 3974883 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2996. Min Range: -9.2996
Max Act: 9.1121. Min Act: -0.1700
Data Index: 6003289 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9871. Min Act: -0.1700
Data Index: 4610789 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9871. Min Act: -0.1700
Data Index: 7952969 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9871. Min Act: -0.1700
Data Index: 5552119 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9871. Min Act: -0.1700
Data Index: 3418061 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9246. Min Act: -0.1700
Data Index: 4127415 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9246. Min Act: -0.1700
Data Index: 572137 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9246. Min Act: -0.1700
Data Index: 8694993 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9246. Min Act: -0.1700
Data Index: 8200284 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.9246. Min Act: -0.1700
Data Index: 6916853 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.8621. Min Act: -0.1700
Data Index: 720464 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.7996. Min Act: -0.1700
Data Index: 5068814 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.7996. Min Act: -0.1700
Data Index: 5082351 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2996. Min Range: -9.2996
Max Act: 8.7996. Min Act: -0.1700
Data Index: 2606956 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19