Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.5680. Min Act: -0.1700
Data Index: 3573895 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.1930. Min Act: -0.1700
Data Index: 7440463 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.1305. Min Act: -0.1700
Data Index: 7903566 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.1305. Min Act: -0.1700
Data Index: 4802504 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.0992. Min Act: -0.1700
Data Index: 7636137 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.0992. Min Act: -0.1700
Data Index: 4825432 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.0680. Min Act: -0.1700
Data Index: 7533884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.0680. Min Act: -0.1700
Data Index: 2029672 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.0367. Min Act: -0.1700
Data Index: 4738401 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9742. Min Act: -0.1700
Data Index: 6552951 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5680. Min Range: -5.5680
Max Act: 5.0055. Min Act: -0.1700
Data Index: 5604792 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9742. Min Act: -0.1700
Data Index: 2019047 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9742. Min Act: -0.1700
Data Index: 7022385 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9430. Min Act: -0.1700
Data Index: 5749667 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9742. Min Act: -0.1700
Data Index: 2295742 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9430. Min Act: -0.1700
Data Index: 5503010 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9117. Min Act: -0.1700
Data Index: 2309806 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9117. Min Act: -0.1700
Data Index: 1844666 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.9117. Min Act: -0.1700
Data Index: 4968423 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5680. Min Range: -5.5680
Max Act: 4.8805. Min Act: -0.1700
Data Index: 2101414 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19