Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5633 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4285. Min Range: -9.4285
Max Act: 9.4285. Min Act: -0.1700
Data Index: 6874280 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4285. Min Range: -9.4285
Max Act: 9.2410. Min Act: -0.1700
Data Index: 6708859 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4285. Min Range: -9.4285
Max Act: 9.1160. Min Act: -0.1700
Data Index: 1035789 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4285. Min Range: -9.4285
Max Act: 9.1160. Min Act: -0.1700
Data Index: 206791 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4285. Min Range: -9.4285
Max Act: 9.0535. Min Act: -0.1700
Data Index: 539347 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.9910. Min Act: -0.1700
Data Index: 3976729 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.9285. Min Act: -0.1700
Data Index: 6333437 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.9285. Min Act: -0.1700
Data Index: 3812214 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.9285. Min Act: -0.1700
Data Index: 3975913 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.9285. Min Act: -0.1700
Data Index: 2514060 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8660. Min Act: -0.1700
Data Index: 5897691 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8660. Min Act: -0.1700
Data Index: 7011486 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8660. Min Act: -0.1700
Data Index: 5768479 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8660. Min Act: -0.1700
Data Index: 5601175 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8660. Min Act: -0.1700
Data Index: 4481302 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8035. Min Act: -0.1700
Data Index: 1424163 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8035. Min Act: -0.1700
Data Index: 419401 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8035. Min Act: -0.1700
Data Index: 407827 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.8035. Min Act: -0.1700
Data Index: 8514397 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4285. Min Range: -9.4285
Max Act: 8.7410. Min Act: -0.1700
Data Index: 2173868 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19