Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.9829. Min Act: -0.1700
Data Index: 6658645 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.9204. Min Act: -0.1700
Data Index: 501352 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.7329. Min Act: -0.1700
Data Index: 6200118 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.6704. Min Act: -0.1700
Data Index: 7484500 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.6704. Min Act: -0.1700
Data Index: 1941775 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.6079. Min Act: -0.1700
Data Index: 3937329 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.6079. Min Act: -0.1700
Data Index: 4982869 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.6704. Min Act: -0.1700
Data Index: 3705909 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.5454. Min Act: -0.1700
Data Index: 162566 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.5454. Min Act: -0.1700
Data Index: 525362 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.5454. Min Act: -0.1700
Data Index: 1378991 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.5454. Min Act: -0.1700
Data Index: 6309819 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.5454. Min Act: -0.1700
Data Index: 4320499 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.4829. Min Act: -0.1700
Data Index: 5981237 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.4829. Min Act: -0.1700
Data Index: 2233333 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.4829. Min Act: -0.1700
Data Index: 2549465 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.4829. Min Act: -0.1700
Data Index: 6118807 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.4204. Min Act: -0.1700
Data Index: 8541276 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.3891. Min Act: -0.1700
Data Index: 121989 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9829. Min Range: -7.9829
Max Act: 7.3579. Min Act: -0.1700
Data Index: 5068017 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19