Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1369 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0872. Min Range: -9.0872
Max Act: 9.0872. Min Act: -0.1700
Data Index: 2598854 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0872. Min Range: -9.0872
Max Act: 9.0247. Min Act: -0.1700
Data Index: 4938556 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.6497. Min Act: -0.1700
Data Index: 1665883 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.5872. Min Act: -0.1700
Data Index: 6776821 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.5872. Min Act: -0.1700
Data Index: 4617390 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.5872. Min Act: -0.1700
Data Index: 7008639 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.4622. Min Act: -0.1700
Data Index: 4453290 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.4622. Min Act: -0.1700
Data Index: 8595586 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.3372. Min Act: -0.1700
Data Index: 2678415 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.3372. Min Act: -0.1700
Data Index: 3209590 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.3372. Min Act: -0.1700
Data Index: 1271332 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.3372. Min Act: -0.1700
Data Index: 5611661 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.3372. Min Act: -0.1700
Data Index: 1425990 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.2747. Min Act: -0.1700
Data Index: 3683467 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.2747. Min Act: -0.1700
Data Index: 902232 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.2747. Min Act: -0.1700
Data Index: 6604875 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.2747. Min Act: -0.1700
Data Index: 5459614 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.2747. Min Act: -0.1700
Data Index: 3470353 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.2122. Min Act: -0.1700
Data Index: 1562156 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0872. Min Range: -9.0872
Max Act: 8.2122. Min Act: -0.1700
Data Index: 4223367 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19