Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1348. Min Range: -6.1348
Max Act: 6.1348. Min Act: -0.1700
Data Index: 7106596 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1348. Min Range: -6.1348
Max Act: 6.0098. Min Act: -0.1700
Data Index: 3210698 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.9785. Min Act: -0.1700
Data Index: 7880389 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.9785. Min Act: -0.1700
Data Index: 7270326 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.9160. Min Act: -0.1700
Data Index: 6934760 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.9160. Min Act: -0.1700
Data Index: 346243 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.8848. Min Act: -0.1700
Data Index: 5450036 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.8535. Min Act: -0.1700
Data Index: 7762843 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.8535. Min Act: -0.1700
Data Index: 670931 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.8535. Min Act: -0.1700
Data Index: 4674804 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7910. Min Act: -0.1700
Data Index: 342061 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7910. Min Act: -0.1700
Data Index: 7504769 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7910. Min Act: -0.1700
Data Index: 7252853 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.8223. Min Act: -0.1700
Data Index: 5613987 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7598. Min Act: -0.1700
Data Index: 6529854 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7598. Min Act: -0.1700
Data Index: 1454473 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7598. Min Act: -0.1700
Data Index: 6440343 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7285. Min Act: -0.1700
Data Index: 6073173 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7598. Min Act: -0.1700
Data Index: 1878732 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1348. Min Range: -6.1348
Max Act: 5.7910. Min Act: -0.1700
Data Index: 1018311 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19