Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.4048. Min Act: -0.1700
Data Index: 712279 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.3423. Min Act: -0.1700
Data Index: 1652779 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.3423. Min Act: -0.1700
Data Index: 4666416 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.2798. Min Act: -0.1700
Data Index: 5270726 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.2173. Min Act: -0.1700
Data Index: 458408 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.2173. Min Act: -0.1700
Data Index: 5765584 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.1548. Min Act: -0.1700
Data Index: 5720573 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.1548. Min Act: -0.1700
Data Index: 7124820 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.0298. Min Act: -0.1700
Data Index: 4708467 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.0298. Min Act: -0.1700
Data Index: 8100030 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4048. Min Range: -9.4048
Max Act: 9.0298. Min Act: -0.1700
Data Index: 8348904 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.9673. Min Act: -0.1700
Data Index: 7637807 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.9673. Min Act: -0.1700
Data Index: 3284942 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.9673. Min Act: -0.1700
Data Index: 1632898 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.8423. Min Act: -0.1700
Data Index: 5801427 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.8423. Min Act: -0.1700
Data Index: 2648372 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.8423. Min Act: -0.1700
Data Index: 6728355 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.8423. Min Act: -0.1700
Data Index: 1137258 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.7798. Min Act: -0.1700
Data Index: 3754785 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4048. Min Range: -9.4048
Max Act: 8.7798. Min Act: -0.1700
Data Index: 6782226 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19