Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4892 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.8807. Min Act: -0.1700
Data Index: 5362566 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.5369. Min Act: -0.1700
Data Index: 7852097 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.5369. Min Act: -0.1700
Data Index: 8724725 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.5369. Min Act: -0.1700
Data Index: 668213 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.4432. Min Act: -0.1700
Data Index: 7485855 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.4119. Min Act: -0.1700
Data Index: 65356 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.4119. Min Act: -0.1700
Data Index: 8511223 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3807. Min Act: -0.1700
Data Index: 4532543 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.4119. Min Act: -0.1700
Data Index: 4782984 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3807. Min Act: -0.1700
Data Index: 8803943 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3807. Min Act: -0.1700
Data Index: 8748531 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3494. Min Act: -0.1700
Data Index: 6492176 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3494. Min Act: -0.1700
Data Index: 4463419 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3494. Min Act: -0.1700
Data Index: 271127 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3494. Min Act: -0.1700
Data Index: 843809 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3494. Min Act: -0.1700
Data Index: 374939 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3494. Min Act: -0.1700
Data Index: 7895607 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3494. Min Act: -0.1700
Data Index: 248769 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.3182. Min Act: -0.1700
Data Index: 3493818 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8807. Min Range: -4.8807
Max Act: 4.2869. Min Act: -0.1700
Data Index: 6134178 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19