Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5104 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.6433. Min Act: -0.1700
Data Index: 5745736 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.5808. Min Act: -0.1700
Data Index: 1391030 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.3308. Min Act: -0.1700
Data Index: 3579831 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2996. Min Act: -0.1700
Data Index: 5130114 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.3308. Min Act: -0.1700
Data Index: 1559452 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.3308. Min Act: -0.1700
Data Index: 6625211 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2996. Min Act: -0.1700
Data Index: 3742999 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2683. Min Act: -0.1700
Data Index: 2153103 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2683. Min Act: -0.1700
Data Index: 5411950 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2371. Min Act: -0.1700
Data Index: 1905522 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2371. Min Act: -0.1700
Data Index: 1623724 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2058. Min Act: -0.1700
Data Index: 523015 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2058. Min Act: -0.1700
Data Index: 948858 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.2058. Min Act: -0.1700
Data Index: 8246134 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.1746. Min Act: -0.1700
Data Index: 3791144 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.1746. Min Act: -0.1700
Data Index: 1949515 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.1746. Min Act: -0.1700
Data Index: 1635587 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.1433. Min Act: -0.1700
Data Index: 7927020 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.1746. Min Act: -0.1700
Data Index: 1156017 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6433. Min Range: -6.6433
Max Act: 6.1746. Min Act: -0.1700
Data Index: 1151264 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19