Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5008 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1031. Min Range: -9.1031
Max Act: 9.1031. Min Act: -0.1700
Data Index: 293555 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.9156. Min Act: -0.1700
Data Index: 1435334 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.8531. Min Act: -0.1700
Data Index: 2158008 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.7281. Min Act: -0.1700
Data Index: 5748244 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.6656. Min Act: -0.1700
Data Index: 5823233 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.6031. Min Act: -0.1700
Data Index: 6519064 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.6656. Min Act: -0.1700
Data Index: 4030951 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.5406. Min Act: -0.1700
Data Index: 2898016 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.5406. Min Act: -0.1700
Data Index: 4093855 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.4781. Min Act: -0.1700
Data Index: 6910598 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.4781. Min Act: -0.1700
Data Index: 8295559 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.4156. Min Act: -0.1700
Data Index: 5020443 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.4156. Min Act: -0.1700
Data Index: 7116744 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.3531. Min Act: -0.1700
Data Index: 7436747 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.3531. Min Act: -0.1700
Data Index: 112258 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.3531. Min Act: -0.1700
Data Index: 4138928 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.3531. Min Act: -0.1700
Data Index: 5077806 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.2281. Min Act: -0.1700
Data Index: 494011 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.2281. Min Act: -0.1700
Data Index: 4602932 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1031. Min Range: -9.1031
Max Act: 8.2281. Min Act: -0.1700
Data Index: 6755929 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19