Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1569 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.7047. Min Act: -0.1698
Data Index: 2233215 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.7047. Min Act: -0.1700
Data Index: 977350 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.6422. Min Act: -0.1699
Data Index: 1622867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.6110. Min Act: -0.1700
Data Index: 1028648 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 3876766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.5485. Min Act: -0.1700
Data Index: 891827 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.5485. Min Act: -0.1696
Data Index: 4974482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 3095136 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.4860. Min Act: -0.1700
Data Index: 4968826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.4547. Min Act: -0.1700
Data Index: 970431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.4547. Min Act: -0.1700
Data Index: 6228097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.4547. Min Act: -0.1700
Data Index: 5994148 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.4547. Min Act: -0.1700
Data Index: 5422362 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.4547. Min Act: -0.1699
Data Index: 2360890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.3297. Min Act: -0.1687
Data Index: 5820415 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.3922. Min Act: -0.1700
Data Index: 5441400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.3610. Min Act: -0.1699
Data Index: 3876130 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.3610. Min Act: -0.1689
Data Index: 533742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.3610. Min Act: -0.1700
Data Index: 8426994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7047. Min Range: -5.7047
Max Act: 5.3297. Min Act: -0.1699
Data Index: 8535279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19