Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2842. Min Range: -7.2842
Max Act: 7.2842. Min Act: -0.1700
Data Index: 7679180 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2842. Min Range: -7.2842
Max Act: 7.0342. Min Act: -0.1700
Data Index: 3944565 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2842. Min Range: -7.2842
Max Act: 7.0654. Min Act: -0.1700
Data Index: 6999100 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2842. Min Range: -7.2842
Max Act: 7.0029. Min Act: -0.1700
Data Index: 2272076 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.9404. Min Act: -0.1700
Data Index: 2935045 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.9092. Min Act: -0.1700
Data Index: 2352922 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.8779. Min Act: -0.1700
Data Index: 5978577 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.8154. Min Act: -0.1700
Data Index: 5521118 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.7842. Min Act: -0.1700
Data Index: 6994468 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.8154. Min Act: -0.1700
Data Index: 29236 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.7217. Min Act: -0.1700
Data Index: 1845515 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.7217. Min Act: -0.1700
Data Index: 2196330 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.7217. Min Act: -0.1700
Data Index: 5348826 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.6904. Min Act: -0.1700
Data Index: 3280677 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.6904. Min Act: -0.1700
Data Index: 1998375 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.6904. Min Act: -0.1700
Data Index: 1668867 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.6592. Min Act: -0.1700
Data Index: 1100639 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.6279. Min Act: -0.1700
Data Index: 5305363 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.6279. Min Act: -0.1700
Data Index: 5001868 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2842. Min Range: -7.2842
Max Act: 6.6279. Min Act: -0.1700
Data Index: 5067162 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19