Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.4562. Min Act: -0.1700
Data Index: 531971 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.4249. Min Act: -0.1700
Data Index: 2753617 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.4249. Min Act: -0.1700
Data Index: 6180465 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.2062. Min Act: -0.1700
Data Index: 7506786 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.2062. Min Act: -0.1700
Data Index: 1078302 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.1124. Min Act: -0.1700
Data Index: 5038681 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.1124. Min Act: -0.1700
Data Index: 5336340 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.0812. Min Act: -0.1700
Data Index: 8373237 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.0499. Min Act: -0.1700
Data Index: 7525067 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.0499. Min Act: -0.1700
Data Index: 5210137 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.0499. Min Act: -0.1700
Data Index: 250542 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.0499. Min Act: -0.1700
Data Index: 6651065 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4562. Min Range: -6.4562
Max Act: 6.0187. Min Act: -0.1700
Data Index: 6458198 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4562. Min Range: -6.4562
Max Act: 5.9874. Min Act: -0.1700
Data Index: 5863645 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4562. Min Range: -6.4562
Max Act: 5.9874. Min Act: -0.1700
Data Index: 3551988 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4562. Min Range: -6.4562
Max Act: 5.9874. Min Act: -0.1700
Data Index: 793854 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4562. Min Range: -6.4562
Max Act: 5.9874. Min Act: -0.1700
Data Index: 3519512 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4562. Min Range: -6.4562
Max Act: 5.9874. Min Act: -0.1700
Data Index: 2553309 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4562. Min Range: -6.4562
Max Act: 5.9874. Min Act: -0.1700
Data Index: 7004323 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4562. Min Range: -6.4562
Max Act: 5.9562. Min Act: -0.1700
Data Index: 3088823 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19