Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6299 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4227. Min Range: -8.4227
Max Act: 8.4227. Min Act: -0.1700
Data Index: 22037 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4227. Min Range: -8.4227
Max Act: 8.2352. Min Act: -0.1700
Data Index: 5861154 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4227. Min Range: -8.4227
Max Act: 8.1102. Min Act: -0.1700
Data Index: 7914818 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4227. Min Range: -8.4227
Max Act: 8.0477. Min Act: -0.1700
Data Index: 6414008 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.9852. Min Act: -0.1700
Data Index: 6340401 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.9852. Min Act: -0.1700
Data Index: 3295834 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.9227. Min Act: -0.1700
Data Index: 3399234 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.9227. Min Act: -0.1700
Data Index: 110536 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.9227. Min Act: -0.1700
Data Index: 3594779 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.8602. Min Act: -0.1700
Data Index: 5825384 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.8602. Min Act: -0.1700
Data Index: 2345730 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 6978927 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 552913 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 7826839 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 3109934 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 757706 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.8602. Min Act: -0.1700
Data Index: 4988735 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 6355888 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 6175564 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4227. Min Range: -8.4227
Max Act: 7.7977. Min Act: -0.1700
Data Index: 453561 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19