Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.3899. Min Act: -0.1700
Data Index: 2879267 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.3899. Min Act: -0.1700
Data Index: 6247391 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.1399. Min Act: -0.1700
Data Index: 5185188 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.1399. Min Act: -0.1700
Data Index: 2867994 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.1087. Min Act: -0.1700
Data Index: 7684754 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0774. Min Act: -0.1700
Data Index: 5185181 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0774. Min Act: -0.1700
Data Index: 915690 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0462. Min Act: -0.1700
Data Index: 6630542 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0462. Min Act: -0.1700
Data Index: 4489157 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0149. Min Act: -0.1700
Data Index: 860060 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0149. Min Act: -0.1700
Data Index: 6630540 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0149. Min Act: -0.1700
Data Index: 871625 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3899. Min Range: -6.3899
Max Act: 5.9837. Min Act: -0.1700
Data Index: 7504256 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3899. Min Range: -6.3899
Max Act: 5.9837. Min Act: -0.1700
Data Index: 3264983 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3899. Min Range: -6.3899
Max Act: 6.0149. Min Act: -0.1700
Data Index: 5185187 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3899. Min Range: -6.3899
Max Act: 5.9837. Min Act: -0.1700
Data Index: 1699779 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3899. Min Range: -6.3899
Max Act: 5.9524. Min Act: -0.1700
Data Index: 2804228 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3899. Min Range: -6.3899
Max Act: 5.9524. Min Act: -0.1700
Data Index: 5127805 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3899. Min Range: -6.3899
Max Act: 5.9524. Min Act: -0.1699
Data Index: 6336616 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3899. Min Range: -6.3899
Max Act: 5.9212. Min Act: -0.1700
Data Index: 21106 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19