Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3383 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.7254. Min Act: -0.1700
Data Index: 6601866 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.6629. Min Act: -0.1700
Data Index: 2177506 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.6004. Min Act: -0.1700
Data Index: 6270012 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.5379. Min Act: -0.1700
Data Index: 8510907 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.4754. Min Act: -0.1700
Data Index: 1193512 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.4754. Min Act: -0.1700
Data Index: 2097906 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.4129. Min Act: -0.1700
Data Index: 1517053 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.4129. Min Act: -0.1700
Data Index: 3407479 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.4129. Min Act: -0.1700
Data Index: 7818981 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.4129. Min Act: -0.1700
Data Index: 6589808 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.3504. Min Act: -0.1700
Data Index: 1543364 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.3504. Min Act: -0.1700
Data Index: 3106135 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.3504. Min Act: -0.1700
Data Index: 1179875 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.3504. Min Act: -0.1700
Data Index: 414190 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.2879. Min Act: -0.1700
Data Index: 5347106 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.2879. Min Act: -0.1700
Data Index: 5920790 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.2879. Min Act: -0.1700
Data Index: 2771464 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.2879. Min Act: -0.1700
Data Index: 2621898 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.2879. Min Act: -0.1700
Data Index: 70259 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7254. Min Range: -8.7254
Max Act: 8.2254. Min Act: -0.1700
Data Index: 5764204 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19