Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0698. Min Range: -6.0698
Max Act: 6.0698. Min Act: -0.1700
Data Index: 4145614 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0698. Min Range: -6.0698
Max Act: 6.0073. Min Act: -0.1700
Data Index: 8495536 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.8198. Min Act: -0.1700
Data Index: 7249302 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.6948. Min Act: -0.1700
Data Index: 4757196 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.6636. Min Act: -0.1700
Data Index: 5978937 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.6636. Min Act: -0.1700
Data Index: 3630757 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.6323. Min Act: -0.1700
Data Index: 5520208 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.6323. Min Act: -0.1700
Data Index: 5481539 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.6323. Min Act: -0.1700
Data Index: 6615183 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.5698. Min Act: -0.1700
Data Index: 5812227 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.5386. Min Act: -0.1700
Data Index: 5407268 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.5386. Min Act: -0.1700
Data Index: 5492114 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.5386. Min Act: -0.1700
Data Index: 7815129 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.5073. Min Act: -0.1700
Data Index: 7727745 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.5073. Min Act: -0.1700
Data Index: 6060852 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.5073. Min Act: -0.1700
Data Index: 4785793 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.4761. Min Act: -0.1700
Data Index: 2410536 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.4761. Min Act: -0.1700
Data Index: 1621485 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.4761. Min Act: -0.1700
Data Index: 2894779 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0698. Min Range: -6.0698
Max Act: 5.4761. Min Act: -0.1700
Data Index: 4252521 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19