Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.8698. Min Act: -0.1700
Data Index: 850594 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.7448. Min Act: -0.1700
Data Index: 4163627 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.6823. Min Act: -0.1700
Data Index: 6581694 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.6511. Min Act: -0.1700
Data Index: 1472889 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5886. Min Act: -0.1700
Data Index: 5235335 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5886. Min Act: -0.1700
Data Index: 7872558 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5886. Min Act: -0.1700
Data Index: 540184 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5573. Min Act: -0.1700
Data Index: 478995 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5261. Min Act: -0.1700
Data Index: 3192027 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5261. Min Act: -0.1700
Data Index: 3701785 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5261. Min Act: -0.1700
Data Index: 5501547 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4948. Min Act: -0.1700
Data Index: 4293094 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.5261. Min Act: -0.1700
Data Index: 7590247 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4323. Min Act: -0.1700
Data Index: 2178621 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4323. Min Act: -0.1700
Data Index: 248958 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4636. Min Act: -0.1700
Data Index: 7463833 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4948. Min Act: -0.1700
Data Index: 1383171 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4323. Min Act: -0.1700
Data Index: 8411555 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4323. Min Act: -0.1700
Data Index: 1767772 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8698. Min Range: -7.8698
Max Act: 7.4323. Min Act: -0.1700
Data Index: 2794227 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19