Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3739 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.7947. Min Act: -0.1700
Data Index: 1526461 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.7322. Min Act: -0.1700
Data Index: 6150872 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.7322. Min Act: -0.1700
Data Index: 6813445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.7009. Min Act: -0.1700
Data Index: 8442992 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.7009. Min Act: -0.1700
Data Index: 7280241 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.7009. Min Act: -0.1700
Data Index: 6178835 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 8560214 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 7371667 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 7006532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 7280975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 2997563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 1986868 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 8752836 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 5482354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6696. Min Act: -0.1700
Data Index: 636531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6383. Min Act: -0.1700
Data Index: 6952764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6383. Min Act: -0.1698
Data Index: 2846122 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6383. Min Act: -0.1700
Data Index: 1246453 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6383. Min Act: -0.1700
Data Index: 5780789 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7947. Min Range: -3.7947
Max Act: 3.6383. Min Act: -0.1700
Data Index: 6703617 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19