Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7991. Min Act: -0.1700
Data Index: 4895933 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7053. Min Act: -0.1700
Data Index: 5470132 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.7053. Min Act: -0.1700
Data Index: 5824012 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.6741. Min Act: -0.1700
Data Index: 1607435 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.6428. Min Act: -0.1700
Data Index: 7630253 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.6428. Min Act: -0.1700
Data Index: 4887375 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.6116. Min Act: -0.1700
Data Index: 877890 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.6116. Min Act: -0.1700
Data Index: 5199829 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5803. Min Act: -0.1700
Data Index: 3043849 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5803. Min Act: -0.1700
Data Index: 7758639 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5803. Min Act: -0.1700
Data Index: 5495125 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 2799183 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 6845048 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 6806776 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 861216 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 6535127 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 863754 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5491. Min Act: -0.1700
Data Index: 7293029 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5178. Min Act: -0.1700
Data Index: 4063867 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7991. Min Range: -4.7991
Max Act: 4.5178. Min Act: -0.1700
Data Index: 4258180 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19