Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2010 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.7058. Min Act: -0.1699
Data Index: 5086153 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.5808. Min Act: -0.1700
Data Index: 2110319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4871. Min Act: -0.1700
Data Index: 2410187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4871. Min Act: -0.1700
Data Index: 7787409 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4871. Min Act: -0.1700
Data Index: 4951943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4558. Min Act: -0.1700
Data Index: 931428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4871. Min Act: -0.1695
Data Index: 6447178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4558. Min Act: -0.1700
Data Index: 8076503 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1699
Data Index: 1462586 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4558. Min Act: -0.1700
Data Index: 7594824 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1700
Data Index: 2006050 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1700
Data Index: 1333950 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1700
Data Index: 5994279 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.3933. Min Act: -0.1693
Data Index: 5969176 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1700
Data Index: 5687220 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1696
Data Index: 6453170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1694
Data Index: 5460205 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.3933. Min Act: -0.1700
Data Index: 2152089 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1700
Data Index: 5259305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7058. Min Range: -6.7058
Max Act: 6.4246. Min Act: -0.1700
Data Index: 4434523 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19