Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6175 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.8016. Min Act: -0.1700
Data Index: 8770533 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.8016. Min Act: -0.1700
Data Index: 6743542 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.7391. Min Act: -0.1700
Data Index: 5244949 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.6766. Min Act: -0.1700
Data Index: 7782242 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.5204. Min Act: -0.1700
Data Index: 1896966 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.5204. Min Act: -0.1700
Data Index: 85358 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.4579. Min Act: -0.1700
Data Index: 7330843 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.4579. Min Act: -0.1700
Data Index: 4058754 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.4266. Min Act: -0.1700
Data Index: 7230911 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.3954. Min Act: -0.1700
Data Index: 6216884 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.3641. Min Act: -0.1700
Data Index: 6184861 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.3329. Min Act: -0.1700
Data Index: 1907034 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.2704. Min Act: -0.1700
Data Index: 3104397 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.2704. Min Act: -0.1700
Data Index: 2339547 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.3329. Min Act: -0.1700
Data Index: 6683820 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.2704. Min Act: -0.1700
Data Index: 6111047 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.2391. Min Act: -0.1700
Data Index: 4277610 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.2079. Min Act: -0.1700
Data Index: 915370 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.2079. Min Act: -0.1700
Data Index: 8508580 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8016. Min Range: -7.8016
Max Act: 7.2079. Min Act: -0.1700
Data Index: 1689334 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19