Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.8813. Min Act: -0.1700
Data Index: 1898460 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.7251. Min Act: -0.1700
Data Index: 4288671 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6938. Min Act: -0.1700
Data Index: 4855380 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6938. Min Act: -0.1700
Data Index: 6243610 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 4613913 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5688. Min Act: -0.1700
Data Index: 3925412 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5376. Min Act: -0.1700
Data Index: 1996411 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5688. Min Act: -0.1700
Data Index: 8345616 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5063. Min Act: -0.1700
Data Index: 6692235 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5063. Min Act: -0.1700
Data Index: 1868907 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.4751. Min Act: -0.1700
Data Index: 1240675 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.4438. Min Act: -0.1700
Data Index: 6703833 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.4751. Min Act: -0.1700
Data Index: 1501841 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.4438. Min Act: -0.1700
Data Index: 5349320 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.4438. Min Act: -0.1700
Data Index: 338615 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.4126. Min Act: -0.1700
Data Index: 6593076 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.3501. Min Act: -0.1700
Data Index: 6427793 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.3501. Min Act: -0.1700
Data Index: 3864800 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.3188. Min Act: -0.1700
Data Index: 2374950 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.3188. Min Act: -0.1700
Data Index: 8147807 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19