Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4684 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4869. Min Act: -0.1700
Data Index: 3723996 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4694. Min Act: -0.1700
Data Index: 3723999 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724012 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3723994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3723998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724013 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724008 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3723997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724003 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724001 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724002 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4518. Min Act: -0.1700
Data Index: 3724011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4869. Min Range: -1.4869
Max Act: 1.4342. Min Act: -0.1700
Data Index: 3723995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19