Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4505 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.7716. Min Act: -0.1700
Data Index: 1516087 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.7091. Min Act: -0.1700
Data Index: 3574370 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.5528. Min Act: -0.1700
Data Index: 219801 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.5216. Min Act: -0.1700
Data Index: 7681508 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.4903. Min Act: -0.1700
Data Index: 3751435 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.4903. Min Act: -0.1700
Data Index: 7786331 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.4903. Min Act: -0.1700
Data Index: 2082913 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.4591. Min Act: -0.1700
Data Index: 3639807 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.4278. Min Act: -0.1700
Data Index: 313558 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.4278. Min Act: -0.1700
Data Index: 2607156 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.4278. Min Act: -0.1700
Data Index: 7355642 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3966. Min Act: -0.1700
Data Index: 8700122 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3966. Min Act: -0.1700
Data Index: 7156241 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3653. Min Act: -0.1700
Data Index: 4916388 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3341. Min Act: -0.1700
Data Index: 7447979 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3028. Min Act: -0.1700
Data Index: 3290559 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3028. Min Act: -0.1700
Data Index: 2841892 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3028. Min Act: -0.1700
Data Index: 2905876 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.3028. Min Act: -0.1700
Data Index: 4871907 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7716. Min Range: -5.7716
Max Act: 5.2716. Min Act: -0.1700
Data Index: 3520075 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19