Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.8281. Min Act: -0.1700
Data Index: 7730687 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.5156. Min Act: -0.1700
Data Index: 3116078 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.4531. Min Act: -0.1700
Data Index: 6898599 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.3594. Min Act: -0.1700
Data Index: 8187603 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.3594. Min Act: -0.1700
Data Index: 3395438 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.3594. Min Act: -0.1700
Data Index: 3693499 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2969. Min Act: -0.1700
Data Index: 1824191 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2969. Min Act: -0.1700
Data Index: 4469157 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2656. Min Act: -0.1700
Data Index: 8787745 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2344. Min Act: -0.1700
Data Index: 7060587 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2031. Min Act: -0.1700
Data Index: 1712465 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2344. Min Act: -0.1700
Data Index: 612989 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2031. Min Act: -0.1700
Data Index: 6098673 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2031. Min Act: -0.1700
Data Index: 2556887 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.2031. Min Act: -0.1700
Data Index: 6284504 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.1719. Min Act: -0.1700
Data Index: 268287 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.1406. Min Act: -0.1700
Data Index: 7814088 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.1719. Min Act: -0.1700
Data Index: 5476018 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.1406. Min Act: -0.1700
Data Index: 7357667 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8281. Min Range: -7.8281
Max Act: 7.1406. Min Act: -0.1700
Data Index: 872327 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19