Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1180. Min Range: -9.1180
Max Act: 9.1180. Min Act: -0.1700
Data Index: 8239035 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1180. Min Range: -9.1180
Max Act: 9.0555. Min Act: -0.1700
Data Index: 637013 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1180. Min Range: -9.1180
Max Act: 9.0555. Min Act: -0.1700
Data Index: 4227950 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1180. Min Range: -9.1180
Max Act: 9.0555. Min Act: -0.1700
Data Index: 3210989 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.9305. Min Act: -0.1700
Data Index: 8181341 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.9305. Min Act: -0.1700
Data Index: 6598884 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.9305. Min Act: -0.1700
Data Index: 4499961 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.8680. Min Act: -0.1700
Data Index: 1757364 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.9305. Min Act: -0.1700
Data Index: 6216472 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.8680. Min Act: -0.1700
Data Index: 2789706 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.8680. Min Act: -0.1700
Data Index: 8161599 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.8055. Min Act: -0.1700
Data Index: 2481534 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.8055. Min Act: -0.1700
Data Index: 3885643 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.7430. Min Act: -0.1700
Data Index: 2458503 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.7430. Min Act: -0.1700
Data Index: 6598870 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.7430. Min Act: -0.1700
Data Index: 2157937 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.6805. Min Act: -0.1700
Data Index: 314607 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.6805. Min Act: -0.1700
Data Index: 4945766 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.6805. Min Act: -0.1700
Data Index: 2452006 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1180. Min Range: -9.1180
Max Act: 8.6180. Min Act: -0.1700
Data Index: 529902 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19