Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.2285. Min Act: -0.1700
Data Index: 7128431 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1972. Min Act: -0.1700
Data Index: 5453076 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1972. Min Act: -0.1700
Data Index: 6289250 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1660. Min Act: -0.1700
Data Index: 2587812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1347. Min Act: -0.1700
Data Index: 8392188 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1347. Min Act: -0.1700
Data Index: 1850873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1035. Min Act: -0.1700
Data Index: 4378724 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1035. Min Act: -0.1700
Data Index: 1836542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1035. Min Act: -0.1700
Data Index: 6605144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1035. Min Act: -0.1700
Data Index: 2629957 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1035. Min Act: -0.1700
Data Index: 5407901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.1035. Min Act: -0.1700
Data Index: 691943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 3698975 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 3319229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 8057532 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 8300019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 3941878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 8568166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 8693640 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2285. Min Range: -4.2285
Max Act: 4.0722. Min Act: -0.1700
Data Index: 3842375 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19