Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.8290. Min Act: -0.1700
Data Index: 8551867 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.6727. Min Act: -0.1700
Data Index: 1512442 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.6102. Min Act: -0.1700
Data Index: 841576 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.6102. Min Act: -0.1700
Data Index: 331917 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.5790. Min Act: -0.1700
Data Index: 3266606 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.5790. Min Act: -0.1700
Data Index: 7369709 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.5790. Min Act: -0.1700
Data Index: 576219 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.5165. Min Act: -0.1700
Data Index: 8484930 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.4540. Min Act: -0.1700
Data Index: 6148 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3915. Min Act: -0.1700
Data Index: 4926355 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3915. Min Act: -0.1700
Data Index: 6777269 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3602. Min Act: -0.1700
Data Index: 8200802 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3602. Min Act: -0.1700
Data Index: 2424418 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3602. Min Act: -0.1700
Data Index: 4324196 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3290. Min Act: -0.1700
Data Index: 3797401 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3602. Min Act: -0.1700
Data Index: 1763079 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3290. Min Act: -0.1700
Data Index: 3166605 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3290. Min Act: -0.1700
Data Index: 2877719 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3290. Min Act: -0.1700
Data Index: 8100659 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8290. Min Range: -5.8290
Max Act: 5.3290. Min Act: -0.1700
Data Index: 3568061 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19