Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.9062. Min Act: -0.1700
Data Index: 5432209 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.8437. Min Act: -0.1700
Data Index: 5036047 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.8125. Min Act: -0.1700
Data Index: 2127475 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.8125. Min Act: -0.1700
Data Index: 138608 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7812. Min Act: -0.1700
Data Index: 7391514 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7812. Min Act: -0.1698
Data Index: 994359 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7812. Min Act: -0.1700
Data Index: 2250771 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7500. Min Act: -0.1700
Data Index: 4691417 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7500. Min Act: -0.1700
Data Index: 1546615 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7500. Min Act: -0.1700
Data Index: 5568892 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7187. Min Act: -0.1700
Data Index: 5389996 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.7500. Min Act: -0.1700
Data Index: 6734218 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6875. Min Act: -0.1699
Data Index: 3902346 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6875. Min Act: -0.1700
Data Index: 8815213 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6562. Min Act: -0.1698
Data Index: 2088879 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6875. Min Act: -0.1700
Data Index: 4385988 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6875. Min Act: -0.1700
Data Index: 7239329 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6562. Min Act: -0.1700
Data Index: 5814584 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6562. Min Act: -0.1700
Data Index: 6549152 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9062. Min Range: -4.9062
Max Act: 4.6250. Min Act: -0.1700
Data Index: 7073487 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19