Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.4753. Min Act: -0.1700
Data Index: 2541235 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.3816. Min Act: -0.1700
Data Index: 8325455 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.1003. Min Act: -0.1700
Data Index: 2001550 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.1003. Min Act: -0.1700
Data Index: 6015808 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.0691. Min Act: -0.1700
Data Index: 4012070 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.0378. Min Act: -0.1700
Data Index: 6653177 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.0066. Min Act: -0.1700
Data Index: 7324316 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.0066. Min Act: -0.1700
Data Index: 5520499 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9753. Min Act: -0.1700
Data Index: 3912487 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9753. Min Act: -0.1700
Data Index: 7534760 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9753. Min Act: -0.1700
Data Index: 5412144 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9753. Min Act: -0.1700
Data Index: 4426472 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9441. Min Act: -0.1700
Data Index: 7396131 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4753. Min Range: -6.4753
Max Act: 6.0066. Min Act: -0.1700
Data Index: 1873107 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9753. Min Act: -0.1700
Data Index: 4024454 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9441. Min Act: -0.1700
Data Index: 2361231 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9441. Min Act: -0.1700
Data Index: 327614 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9441. Min Act: -0.1700
Data Index: 7068642 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9441. Min Act: -0.1700
Data Index: 91517 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4753. Min Range: -6.4753
Max Act: 5.9441. Min Act: -0.1700
Data Index: 3073154 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19