Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2141. Min Range: -6.2141
Max Act: 6.2141. Min Act: -0.1700
Data Index: 619262 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2141. Min Range: -6.2141
Max Act: 6.1516. Min Act: -0.1700
Data Index: 4319053 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2141. Min Range: -6.2141
Max Act: 6.0891. Min Act: -0.1700
Data Index: 8600264 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.9328. Min Act: -0.1700
Data Index: 3660737 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.9016. Min Act: -0.1700
Data Index: 2556687 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.9016. Min Act: -0.1700
Data Index: 3547642 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.9016. Min Act: -0.1700
Data Index: 2394152 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.9016. Min Act: -0.1700
Data Index: 4994866 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.8703. Min Act: -0.1700
Data Index: 5432423 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.8391. Min Act: -0.1700
Data Index: 1860377 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.7766. Min Act: -0.1700
Data Index: 2375021 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.7766. Min Act: -0.1700
Data Index: 5432424 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.7453. Min Act: -0.1700
Data Index: 3355704 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.7141. Min Act: -0.1700
Data Index: 6684464 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.7141. Min Act: -0.1700
Data Index: 8746399 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.7141. Min Act: -0.1700
Data Index: 7171069 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.6828. Min Act: -0.1700
Data Index: 8037695 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.6828. Min Act: -0.1700
Data Index: 1712960 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.7141. Min Act: -0.1700
Data Index: 3826025 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2141. Min Range: -6.2141
Max Act: 5.6516. Min Act: -0.1700
Data Index: 4730481 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19