Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1758. Min Range: -7.1758
Max Act: 7.1445. Min Act: -0.1700
Data Index: 7472557 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1758. Min Range: -7.1758
Max Act: 7.1758. Min Act: -0.1700
Data Index: 4732102 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1758. Min Range: -7.1758
Max Act: 7.0508. Min Act: -0.1700
Data Index: 4299733 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.9570. Min Act: -0.1700
Data Index: 5107122 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.8945. Min Act: -0.1700
Data Index: 3201994 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.8633. Min Act: -0.1700
Data Index: 2824347 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.8945. Min Act: -0.1700
Data Index: 2890896 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.7383. Min Act: -0.1700
Data Index: 280032 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.7383. Min Act: -0.1700
Data Index: 3181902 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.7383. Min Act: -0.1700
Data Index: 6676909 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.7383. Min Act: -0.1700
Data Index: 7214769 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.7070. Min Act: -0.1700
Data Index: 222201 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.6445. Min Act: -0.1700
Data Index: 5843659 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.6445. Min Act: -0.1700
Data Index: 532853 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.6133. Min Act: -0.1700
Data Index: 274980 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.5508. Min Act: -0.1700
Data Index: 2069320 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.5820. Min Act: -0.1700
Data Index: 8605522 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.5508. Min Act: -0.1700
Data Index: 854983 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.4570. Min Act: -0.1700
Data Index: 1191974 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1758. Min Range: -7.1758
Max Act: 6.4570. Min Act: -0.1700
Data Index: 1972729 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19