Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.6770. Min Act: -0.1700
Data Index: 5144530 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.6458. Min Act: -0.1700
Data Index: 7429739 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.3645. Min Act: -0.1700
Data Index: 6027958 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.2708. Min Act: -0.1700
Data Index: 7950394 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.2708. Min Act: -0.1700
Data Index: 7788718 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.2083. Min Act: -0.1700
Data Index: 8005490 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.1770. Min Act: -0.1700
Data Index: 2599085 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.1770. Min Act: -0.1700
Data Index: 3850978 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.1458. Min Act: -0.1700
Data Index: 6187887 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.1770. Min Act: -0.1700
Data Index: 211283 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.1145. Min Act: -0.1700
Data Index: 2205701 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6770. Min Range: -6.6770
Max Act: 6.1145. Min Act: -0.1700
Data Index: 687531 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9895. Min Act: -0.1700
Data Index: 5089084 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9895. Min Act: -0.1700
Data Index: 8534098 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9895. Min Act: -0.1700
Data Index: 7431981 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9583. Min Act: -0.1700
Data Index: 6533742 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9583. Min Act: -0.1700
Data Index: 7524192 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9583. Min Act: -0.1700
Data Index: 2240771 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9583. Min Act: -0.1700
Data Index: 4142573 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6770. Min Range: -6.6770
Max Act: 5.9583. Min Act: -0.1700
Data Index: 4424287 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19