Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0385. Min Range: -8.0385
Max Act: 8.0385. Min Act: -0.1700
Data Index: 5735255 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.9135. Min Act: -0.1700
Data Index: 5590282 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.7260. Min Act: -0.1700
Data Index: 7026742 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.6635. Min Act: -0.1700
Data Index: 1517285 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 6718908 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 603971 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 137565 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.5073. Min Act: -0.1700
Data Index: 600918 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.5385. Min Act: -0.1700
Data Index: 6898336 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.4135. Min Act: -0.1700
Data Index: 1307379 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.4448. Min Act: -0.1700
Data Index: 440913 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.3823. Min Act: -0.1700
Data Index: 5068352 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.4135. Min Act: -0.1700
Data Index: 358374 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.4135. Min Act: -0.1700
Data Index: 7999231 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.3823. Min Act: -0.1700
Data Index: 1613307 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.3823. Min Act: -0.1700
Data Index: 5865618 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.3823. Min Act: -0.1700
Data Index: 8502494 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.3198. Min Act: -0.1700
Data Index: 4379381 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.3198. Min Act: -0.1700
Data Index: 4002778 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0385. Min Range: -8.0385
Max Act: 7.3198. Min Act: -0.1700
Data Index: 5306043 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19