Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1993 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2867. Min Range: -8.2867
Max Act: 8.2867. Min Act: -0.1700
Data Index: 1401257 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.9117. Min Act: -0.1700
Data Index: 499221 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.8492. Min Act: -0.1700
Data Index: 3827637 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.7867. Min Act: -0.1700
Data Index: 4185377 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.7242. Min Act: -0.1700
Data Index: 582470 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.7242. Min Act: -0.1700
Data Index: 5571375 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.7242. Min Act: -0.1700
Data Index: 2731956 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.6617. Min Act: -0.1700
Data Index: 3441628 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.6617. Min Act: -0.1700
Data Index: 3598334 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.6617. Min Act: -0.1700
Data Index: 6371992 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.5992. Min Act: -0.1700
Data Index: 5693350 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.5992. Min Act: -0.1700
Data Index: 8074062 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.5055. Min Act: -0.1700
Data Index: 8090464 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.5055. Min Act: -0.1700
Data Index: 339883 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.4742. Min Act: -0.1700
Data Index: 538763 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.4742. Min Act: -0.1700
Data Index: 8721235 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.4742. Min Act: -0.1700
Data Index: 2848760 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.4742. Min Act: -0.1700
Data Index: 2284022 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.4742. Min Act: -0.1700
Data Index: 2775164 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2867. Min Range: -8.2867
Max Act: 7.4430. Min Act: -0.1700
Data Index: 650293 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19