Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5772 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.8867. Min Act: -0.1700
Data Index: 3618660 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.7617. Min Act: -0.1700
Data Index: 1641791 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.7617. Min Act: -0.1700
Data Index: 5313960 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.7305. Min Act: -0.1700
Data Index: 2969071 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.6367. Min Act: -0.1700
Data Index: 8759498 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.6367. Min Act: -0.1700
Data Index: 2197907 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.6367. Min Act: -0.1700
Data Index: 5067685 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.6367. Min Act: -0.1700
Data Index: 3037313 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.6055. Min Act: -0.1700
Data Index: 3278521 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.5742. Min Act: -0.1700
Data Index: 6061185 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.6055. Min Act: -0.1700
Data Index: 1457902 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.6055. Min Act: -0.1700
Data Index: 1971073 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.5430. Min Act: -0.1700
Data Index: 6708420 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.5430. Min Act: -0.1700
Data Index: 1449080 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.5117. Min Act: -0.1700
Data Index: 6939165 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.5117. Min Act: -0.1700
Data Index: 7847055 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.5117. Min Act: -0.1700
Data Index: 3479517 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.4805. Min Act: -0.1700
Data Index: 930670 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.4492. Min Act: -0.1700
Data Index: 6528901 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8867. Min Range: -5.8867
Max Act: 5.4180. Min Act: -0.1700
Data Index: 7349315 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19