Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.6738. Min Act: -0.1700
Data Index: 4754689 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.6738. Min Act: -0.1700
Data Index: 7761227 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.3925. Min Act: -0.1700
Data Index: 3701267 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.3613. Min Act: -0.1700
Data Index: 6542902 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.3613. Min Act: -0.1700
Data Index: 8625251 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.3613. Min Act: -0.1700
Data Index: 5709962 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2988. Min Act: -0.1700
Data Index: 3771008 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2675. Min Act: -0.1700
Data Index: 8101321 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2363. Min Act: -0.1700
Data Index: 4835748 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2363. Min Act: -0.1700
Data Index: 3998885 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2363. Min Act: -0.1700
Data Index: 5176710 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2050. Min Act: -0.1700
Data Index: 7173771 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2050. Min Act: -0.1700
Data Index: 4098792 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.1425. Min Act: -0.1700
Data Index: 7409954 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.1738. Min Act: -0.1700
Data Index: 206643 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.2050. Min Act: -0.1700
Data Index: 4722193 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.1738. Min Act: -0.1700
Data Index: 4352902 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.1425. Min Act: -0.1700
Data Index: 3302907 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.1425. Min Act: -0.1700
Data Index: 6354722 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6738. Min Range: -7.6738
Max Act: 7.1425. Min Act: -0.1700
Data Index: 8020043 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19