Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 450 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1085. Min Range: -7.1085
Max Act: 7.0773. Min Act: -0.1700
Data Index: 4203475 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1085. Min Range: -7.1085
Max Act: 7.1085. Min Act: -0.1700
Data Index: 8130701 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1085. Min Range: -7.1085
Max Act: 7.1085. Min Act: -0.1700
Data Index: 4889612 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.9210. Min Act: -0.1700
Data Index: 1818838 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8898. Min Act: -0.1700
Data Index: 2961775 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.9210. Min Act: -0.1700
Data Index: 946609 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8898. Min Act: -0.1700
Data Index: 6766379 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8898. Min Act: -0.1700
Data Index: 7824081 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8273. Min Act: -0.1700
Data Index: 1899752 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8273. Min Act: -0.1700
Data Index: 8691342 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8273. Min Act: -0.1700
Data Index: 5799660 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7960. Min Act: -0.1700
Data Index: 1703328 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7960. Min Act: -0.1700
Data Index: 1978594 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7960. Min Act: -0.1700
Data Index: 7705034 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7960. Min Act: -0.1700
Data Index: 5935220 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7648. Min Act: -0.1700
Data Index: 4413299 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7648. Min Act: -0.1700
Data Index: 7773697 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7648. Min Act: -0.1700
Data Index: 3098571 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7335. Min Act: -0.1700
Data Index: 8181956 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7335. Min Act: -0.1700
Data Index: 5331762 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19