Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.9589. Min Act: -0.1700
Data Index: 2188354 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.9589. Min Act: -0.1700
Data Index: 5706844 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.8339. Min Act: -0.1700
Data Index: 3782089 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7714. Min Act: -0.1700
Data Index: 37717 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7401. Min Act: -0.1700
Data Index: 4892594 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7401. Min Act: -0.1700
Data Index: 4487982 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7714. Min Act: -0.1700
Data Index: 3931023 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7401. Min Act: -0.1700
Data Index: 6795165 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7401. Min Act: -0.1700
Data Index: 5774686 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7089. Min Act: -0.1700
Data Index: 7260513 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7089. Min Act: -0.1700
Data Index: 1380901 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7089. Min Act: -0.1700
Data Index: 5614775 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.7089. Min Act: -0.1700
Data Index: 2313897 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.6776. Min Act: -0.1700
Data Index: 7544002 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.6776. Min Act: -0.1700
Data Index: 8723627 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.6776. Min Act: -0.1700
Data Index: 1038261 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.6776. Min Act: -0.1700
Data Index: 1111860 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.6464. Min Act: -0.1700
Data Index: 1509087 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.6464. Min Act: -0.1700
Data Index: 251577 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9589. Min Range: -5.9589
Max Act: 5.6464. Min Act: -0.1700
Data Index: 5656680 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19