Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2156. Min Range: -6.2156
Max Act: 6.2156. Min Act: -0.1700
Data Index: 4481706 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2156. Min Range: -6.2156
Max Act: 6.1843. Min Act: -0.1700
Data Index: 7014410 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2156. Min Range: -6.2156
Max Act: 6.0281. Min Act: -0.1700
Data Index: 1537715 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.8093. Min Act: -0.1700
Data Index: 1734564 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.6843. Min Act: -0.1700
Data Index: 5354689 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.6531. Min Act: -0.1700
Data Index: 1526153 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.5593. Min Act: -0.1700
Data Index: 1714270 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.5593. Min Act: -0.1700
Data Index: 8372434 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.5593. Min Act: -0.1700
Data Index: 3213191 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 1526154 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.4031. Min Act: -0.1700
Data Index: 1734563 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.4031. Min Act: -0.1700
Data Index: 7414759 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.3718. Min Act: -0.1700
Data Index: 33534 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.2781. Min Act: -0.1700
Data Index: 6319209 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.2781. Min Act: -0.1700
Data Index: 1213344 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.2468. Min Act: -0.1700
Data Index: 2493312 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.2468. Min Act: -0.1700
Data Index: 3213192 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.2156. Min Act: -0.1700
Data Index: 7088833 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.2156. Min Act: -0.1700
Data Index: 5607951 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2156. Min Range: -6.2156
Max Act: 5.2156. Min Act: -0.1700
Data Index: 5184948 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19