Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2713 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7468. Min Range: -8.7468
Max Act: 8.7468. Min Act: -0.1700
Data Index: 1807340 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.7781. Min Act: -0.1700
Data Index: 5533554 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.7468. Min Act: -0.1700
Data Index: 4755941 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.7156. Min Act: -0.1700
Data Index: 109155 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.6218. Min Act: -0.1700
Data Index: 4834 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.4343. Min Act: -0.1700
Data Index: 3913906 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.4031. Min Act: -0.1700
Data Index: 5637961 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.3406. Min Act: -0.1700
Data Index: 477851 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.3406. Min Act: -0.1700
Data Index: 1080615 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.3718. Min Act: -0.1700
Data Index: 121647 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.2781. Min Act: -0.1700
Data Index: 4547681 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.3406. Min Act: -0.1700
Data Index: 4905438 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.2781. Min Act: -0.1700
Data Index: 5908938 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.3093. Min Act: -0.1700
Data Index: 7538272 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.2468. Min Act: -0.1700
Data Index: 3545289 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.2468. Min Act: -0.1700
Data Index: 7003568 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.2156. Min Act: -0.1700
Data Index: 1565432 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.2156. Min Act: -0.1700
Data Index: 2134349 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.2156. Min Act: -0.1700
Data Index: 4503354 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7468. Min Range: -8.7468
Max Act: 7.1843. Min Act: -0.1700
Data Index: 4378993 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19