Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1736 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.8614. Min Act: -0.1700
Data Index: 2035160 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.8301. Min Act: -0.1700
Data Index: 759601 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.7989. Min Act: -0.1700
Data Index: 6659992 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.5801. Min Act: -0.1700
Data Index: 6022614 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.5176. Min Act: -0.1700
Data Index: 7095183 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.5176. Min Act: -0.1700
Data Index: 2955722 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.4864. Min Act: -0.1700
Data Index: 1432263 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.4864. Min Act: -0.1700
Data Index: 5645291 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.4239. Min Act: -0.1700
Data Index: 3768975 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.3926. Min Act: -0.1700
Data Index: 2703465 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2989. Min Act: -0.1700
Data Index: 8410811 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2676. Min Act: -0.1700
Data Index: 5514920 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2989. Min Act: -0.1700
Data Index: 2822536 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2676. Min Act: -0.1700
Data Index: 6098970 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2676. Min Act: -0.1700
Data Index: 1010068 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2676. Min Act: -0.1700
Data Index: 2560414 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2364. Min Act: -0.1700
Data Index: 4605289 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2051. Min Act: -0.1700
Data Index: 6752848 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2051. Min Act: -0.1700
Data Index: 6705817 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8614. Min Range: -6.8614
Max Act: 6.2051. Min Act: -0.1700
Data Index: 2167353 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19