Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.8918. Min Act: -0.1700
Data Index: 4825787 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.8918. Min Act: -0.1700
Data Index: 305953 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.7668. Min Act: -0.1700
Data Index: 6496886 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.7668. Min Act: -0.1700
Data Index: 599653 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.7668. Min Act: -0.1700
Data Index: 6835209 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.7043. Min Act: -0.1700
Data Index: 6977673 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.7043. Min Act: -0.1700
Data Index: 2932257 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.5168. Min Act: -0.1700
Data Index: 5702752 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.5793. Min Act: -0.1700
Data Index: 7638049 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.5168. Min Act: -0.1700
Data Index: 5126936 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.5168. Min Act: -0.1700
Data Index: 6189037 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.5168. Min Act: -0.1700
Data Index: 5086951 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.4543. Min Act: -0.1700
Data Index: 6564320 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.3918. Min Act: -0.1700
Data Index: 3448465 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.3918. Min Act: -0.1700
Data Index: 468258 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.3918. Min Act: -0.1700
Data Index: 5502907 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.3918. Min Act: -0.1700
Data Index: 6997980 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.3918. Min Act: -0.1700
Data Index: 6460172 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.3918. Min Act: -0.1700
Data Index: 538481 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8918. Min Range: -8.8918
Max Act: 8.3918. Min Act: -0.1700
Data Index: 3662611 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19