Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4398 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.5861. Min Act: -0.1700
Data Index: 4753719 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.4924. Min Act: -0.1700
Data Index: 7083819 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.3049. Min Act: -0.1700
Data Index: 3825302 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.2111. Min Act: -0.1700
Data Index: 6809475 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.1799. Min Act: -0.1700
Data Index: 5616935 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.1799. Min Act: -0.1700
Data Index: 582600 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.0861. Min Act: -0.1700
Data Index: 5565916 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.0549. Min Act: -0.1700
Data Index: 4852403 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.0549. Min Act: -0.1700
Data Index: 2250195 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.0236. Min Act: -0.1700
Data Index: 7247379 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9924. Min Act: -0.1700
Data Index: 8049967 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5861. Min Range: -6.5861
Max Act: 6.0236. Min Act: -0.1700
Data Index: 2696161 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9924. Min Act: -0.1700
Data Index: 2155815 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9924. Min Act: -0.1700
Data Index: 3514892 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9924. Min Act: -0.1700
Data Index: 5375032 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9611. Min Act: -0.1700
Data Index: 5669650 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9299. Min Act: -0.1700
Data Index: 6667806 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.8986. Min Act: -0.1700
Data Index: 6879134 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9299. Min Act: -0.1700
Data Index: 3854941 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5861. Min Range: -6.5861
Max Act: 5.9299. Min Act: -0.1700
Data Index: 1431977 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19