Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2691 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3751. Min Range: -12.3751
Max Act: 12.3751. Min Act: -0.1700
Data Index: 7013250 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3751. Min Range: -12.3751
Max Act: 12.1876. Min Act: -0.1700
Data Index: 6618161 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3751. Min Range: -12.3751
Max Act: 12.2501. Min Act: -0.1700
Data Index: 7741804 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.9376. Min Act: -0.1700
Data Index: 2246045 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.7501. Min Act: -0.1700
Data Index: 4311014 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.7501. Min Act: -0.1700
Data Index: 3008362 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.7501. Min Act: -0.1700
Data Index: 4940009 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.6876. Min Act: -0.1700
Data Index: 5257567 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.6251. Min Act: -0.1700
Data Index: 8236011 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.5626. Min Act: -0.1700
Data Index: 5477784 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.5626. Min Act: -0.1700
Data Index: 8601655 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.5626. Min Act: -0.1700
Data Index: 7043827 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.5001. Min Act: -0.1700
Data Index: 7455356 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.5001. Min Act: -0.1700
Data Index: 7455355 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.5001. Min Act: -0.1700
Data Index: 5174214 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.4376. Min Act: -0.1700
Data Index: 2947362 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.4376. Min Act: -0.1700
Data Index: 7929669 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.3751. Min Act: -0.1700
Data Index: 6412339 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.3751. Min Act: -0.1700
Data Index: 7199150 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3751. Min Range: -12.3751
Max Act: 11.3751. Min Act: -0.1700
Data Index: 384305 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19