Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.3267. Min Act: -0.1700
Data Index: 8681292 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.2329. Min Act: -0.1700
Data Index: 4479070 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.2017. Min Act: -0.1700
Data Index: 735706 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1704. Min Act: -0.1700
Data Index: 6948988 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1704. Min Act: -0.1700
Data Index: 5473284 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 5511262 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 6514110 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 5473285 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1079. Min Act: -0.1700
Data Index: 5322777 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1079. Min Act: -0.1700
Data Index: 6514113 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1079. Min Act: -0.1700
Data Index: 5473283 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1079. Min Act: -0.1700
Data Index: 3921866 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.1079. Min Act: -0.1700
Data Index: 5573085 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.0767. Min Act: -0.1700
Data Index: 6026744 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.0767. Min Act: -0.1700
Data Index: 1634830 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.0767. Min Act: -0.1700
Data Index: 1674242 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.0767. Min Act: -0.1700
Data Index: 4355139 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.0767. Min Act: -0.1700
Data Index: 6026721 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.0767. Min Act: -0.1700
Data Index: 5885977 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3267. Min Range: -5.3267
Max Act: 5.0454. Min Act: -0.1700
Data Index: 5549788 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19