Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5603 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7968. Min Act: -0.1700
Data Index: 5493818 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7030. Min Act: -0.1700
Data Index: 712664 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7030. Min Act: -0.1700
Data Index: 3892493 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7030. Min Act: -0.1700
Data Index: 840212 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7030. Min Act: -0.1700
Data Index: 7188674 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.7030. Min Act: -0.1700
Data Index: 4604985 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6718. Min Act: -0.1700
Data Index: 3098460 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6718. Min Act: -0.1700
Data Index: 8216006 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7691589 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6718. Min Act: -0.1700
Data Index: 1405668 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6718. Min Act: -0.1700
Data Index: 7245212 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 2672782 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7864572 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 8198028 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 5310809 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 4213017 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 7022111 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 2436499 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 5522573 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7968. Min Range: -4.7968
Max Act: 4.6405. Min Act: -0.1700
Data Index: 2460791 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19