Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4894 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.7905. Min Act: -0.1700
Data Index: 7410250 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.7905. Min Act: -0.1700
Data Index: 8267136 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.7593. Min Act: -0.1700
Data Index: 5316391 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.7280. Min Act: -0.1700
Data Index: 6553876 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6968. Min Act: -0.1700
Data Index: 8418105 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6655. Min Act: -0.1700
Data Index: 8167712 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6655. Min Act: -0.1700
Data Index: 4468720 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6343. Min Act: -0.1700
Data Index: 2810722 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6030. Min Act: -0.1700
Data Index: 540226 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6030. Min Act: -0.1700
Data Index: 8075420 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6030. Min Act: -0.1700
Data Index: 6213048 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6030. Min Act: -0.1700
Data Index: 222770 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6030. Min Act: -0.1700
Data Index: 6553882 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.6030. Min Act: -0.1700
Data Index: 1463967 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.5718. Min Act: -0.1700
Data Index: 3628506 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.5718. Min Act: -0.1700
Data Index: 1425731 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.5405. Min Act: -0.1700
Data Index: 585877 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.5405. Min Act: -0.1700
Data Index: 215930 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.5405. Min Act: -0.1700
Data Index: 2503396 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7905. Min Range: -5.7905
Max Act: 5.5405. Min Act: -0.1700
Data Index: 8236067 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19