Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1775. Min Range: -9.1775
Max Act: 9.1775. Min Act: -0.1700
Data Index: 5867132 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1775. Min Range: -9.1775
Max Act: 9.1775. Min Act: -0.1700
Data Index: 7915473 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.9275. Min Act: -0.1700
Data Index: 5895942 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.9275. Min Act: -0.1700
Data Index: 6113299 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.7400. Min Act: -0.1700
Data Index: 1140823 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.7400. Min Act: -0.1700
Data Index: 2528601 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.6775. Min Act: -0.1700
Data Index: 6494522 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.6150. Min Act: -0.1700
Data Index: 7198094 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.5525. Min Act: -0.1700
Data Index: 5310391 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.4275. Min Act: -0.1700
Data Index: 2034560 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.4900. Min Act: -0.1700
Data Index: 5221802 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.4275. Min Act: -0.1700
Data Index: 119052 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.4275. Min Act: -0.1700
Data Index: 6301759 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.3025. Min Act: -0.1700
Data Index: 255592 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.3650. Min Act: -0.1700
Data Index: 3459790 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.3025. Min Act: -0.1700
Data Index: 972701 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.3025. Min Act: -0.1700
Data Index: 7094863 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.2400. Min Act: -0.1700
Data Index: 1135726 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.2400. Min Act: -0.1700
Data Index: 5859759 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1775. Min Range: -9.1775
Max Act: 8.1775. Min Act: -0.1699
Data Index: 1187506 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19