Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5612 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3805. Min Range: -8.3805
Max Act: 8.3805. Min Act: -0.1700
Data Index: 3813135 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3805. Min Range: -8.3805
Max Act: 8.3180. Min Act: -0.1700
Data Index: 3964760 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3805. Min Range: -8.3805
Max Act: 8.1305. Min Act: -0.1700
Data Index: 4361114 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3805. Min Range: -8.3805
Max Act: 8.0680. Min Act: -0.1700
Data Index: 821523 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3805. Min Range: -8.3805
Max Act: 8.0680. Min Act: -0.1700
Data Index: 5206724 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3805. Min Range: -8.3805
Max Act: 8.0055. Min Act: -0.1700
Data Index: 3547761 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.9430. Min Act: -0.1700
Data Index: 5733453 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.8805. Min Act: -0.1700
Data Index: 8216495 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.8492. Min Act: -0.1700
Data Index: 6663267 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.8180. Min Act: -0.1700
Data Index: 7487561 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6930. Min Act: -0.1700
Data Index: 7805258 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6617. Min Act: -0.1700
Data Index: 4145283 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6930. Min Act: -0.1700
Data Index: 758190 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6305. Min Act: -0.1700
Data Index: 2936492 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6617. Min Act: -0.1700
Data Index: 8406151 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6617. Min Act: -0.1700
Data Index: 5793806 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6617. Min Act: -0.1700
Data Index: 7429288 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.6305. Min Act: -0.1700
Data Index: 7049733 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.5680. Min Act: -0.1700
Data Index: 6580296 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3805. Min Range: -8.3805
Max Act: 7.5992. Min Act: -0.1700
Data Index: 2036341 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19