Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4129 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3663. Min Act: -0.1700
Data Index: 1228637 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3663. Min Act: -0.1700
Data Index: 5403906 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 1217444 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 8056769 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 3212136 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 3232425 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4096203 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4340874 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4395539 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 1868241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4612016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3035. Min Act: -0.1700
Data Index: 2006148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3035. Min Act: -0.1700
Data Index: 2002548 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4602214 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3035. Min Act: -0.1700
Data Index: 664575 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3035. Min Act: -0.1700
Data Index: 1586410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3349. Min Act: -0.1700
Data Index: 1433009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3035. Min Act: -0.1700
Data Index: 1414102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3035. Min Act: -0.1700
Data Index: 3801976 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3663. Min Range: -3.3663
Max Act: 3.3035. Min Act: -0.1700
Data Index: 60737 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19