Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.8591. Min Act: -0.1700
Data Index: 7901967 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.7029. Min Act: -0.1700
Data Index: 3662599 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.6716. Min Act: -0.1700
Data Index: 5346981 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.6716. Min Act: -0.1700
Data Index: 7174002 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.6404. Min Act: -0.1700
Data Index: 7330737 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.6716. Min Act: -0.1700
Data Index: 8063187 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.6091. Min Act: -0.1700
Data Index: 4473010 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.6091. Min Act: -0.1700
Data Index: 8044522 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5779. Min Act: -0.1700
Data Index: 874294 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5779. Min Act: -0.1700
Data Index: 4762323 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.6091. Min Act: -0.1700
Data Index: 3597629 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5466. Min Act: -0.1700
Data Index: 961022 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5154. Min Act: -0.1700
Data Index: 7629235 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5154. Min Act: -0.1700
Data Index: 8739977 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.4841. Min Act: -0.1700
Data Index: 2036919 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5154. Min Act: -0.1700
Data Index: 4525856 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5154. Min Act: -0.1700
Data Index: 7629234 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5154. Min Act: -0.1700
Data Index: 5974659 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5154. Min Act: -0.1700
Data Index: 7297609 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8591. Min Range: -4.8591
Max Act: 4.5154. Min Act: -0.1700
Data Index: 728958 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19