Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7256. Min Range: -8.7256
Max Act: 8.7256. Min Act: -0.1700
Data Index: 4122472 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.9756. Min Act: -0.1700
Data Index: 6765767 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.9443. Min Act: -0.1700
Data Index: 4016527 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.7256. Min Act: -0.1700
Data Index: 7530866 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.5693. Min Act: -0.1700
Data Index: 1383622 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.5068. Min Act: -0.1700
Data Index: 5129347 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.4756. Min Act: -0.1700
Data Index: 5604127 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.5068. Min Act: -0.1700
Data Index: 7701337 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.5068. Min Act: -0.1700
Data Index: 4088502 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.4443. Min Act: -0.1700
Data Index: 3698906 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.4756. Min Act: -0.1700
Data Index: 6300445 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3506. Min Act: -0.1700
Data Index: 6558230 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3193. Min Act: -0.1700
Data Index: 6759771 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3506. Min Act: -0.1700
Data Index: 8761591 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3506. Min Act: -0.1700
Data Index: 4625242 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3506. Min Act: -0.1700
Data Index: 4522620 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3193. Min Act: -0.1700
Data Index: 7265307 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3193. Min Act: -0.1700
Data Index: 722324 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.2881. Min Act: -0.1700
Data Index: 6290350 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7256. Min Range: -8.7256
Max Act: 7.3193. Min Act: -0.1700
Data Index: 7390763 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19