Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6388 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.7867. Min Act: -0.1700
Data Index: 7180602 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.6617. Min Act: -0.1700
Data Index: 138201 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.6617. Min Act: -0.1700
Data Index: 5354436 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.6617. Min Act: -0.1700
Data Index: 1433110 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.6617. Min Act: -0.1700
Data Index: 3305784 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5992. Min Act: -0.1700
Data Index: 5876703 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5992. Min Act: -0.1700
Data Index: 6991418 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5992. Min Act: -0.1700
Data Index: 797198 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5992. Min Act: -0.1700
Data Index: 8499614 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5367. Min Act: -0.1700
Data Index: 5079178 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5367. Min Act: -0.1700
Data Index: 7297011 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5054. Min Act: -0.1700
Data Index: 5015995 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5054. Min Act: -0.1700
Data Index: 5188888 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.5054. Min Act: -0.1700
Data Index: 5355082 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.4742. Min Act: -0.1700
Data Index: 938122 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.4742. Min Act: -0.1700
Data Index: 1931983 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.4117. Min Act: -0.1700
Data Index: 3451761 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.3804. Min Act: -0.1700
Data Index: 1796854 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.3804. Min Act: -0.1700
Data Index: 4878191 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7867. Min Range: -7.7867
Max Act: 7.4117. Min Act: -0.1700
Data Index: 6240368 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19