Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.9097. Min Act: -0.1700
Data Index: 3081514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.8159. Min Act: -0.1700
Data Index: 6537155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 4897226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7534. Min Act: -0.1700
Data Index: 4363094 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7534. Min Act: -0.1700
Data Index: 810594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 1181125 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7534. Min Act: -0.1700
Data Index: 7765978 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 7747905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 7352097 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 1389739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 7142557 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 5814258 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.7221. Min Act: -0.1700
Data Index: 7776958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.6908. Min Act: -0.1700
Data Index: 2518174 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.6908. Min Act: -0.1700
Data Index: 5551529 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.6908. Min Act: -0.1700
Data Index: 7630484 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.6908. Min Act: -0.1700
Data Index: 5502445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.6908. Min Act: -0.1700
Data Index: 1965122 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.6908. Min Act: -0.1700
Data Index: 4469527 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9097. Min Range: -3.9097
Max Act: 3.6908. Min Act: -0.1700
Data Index: 5183113 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19