Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1875 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.7119. Min Act: -0.1700
Data Index: 3533548 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.6807. Min Act: -0.1700
Data Index: 6080413 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.6182. Min Act: -0.1700
Data Index: 4411317 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.5557. Min Act: -0.1700
Data Index: 3009452 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.5557. Min Act: -0.1700
Data Index: 1064408 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.4307. Min Act: -0.1700
Data Index: 4144508 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3994. Min Act: -0.1700
Data Index: 7028270 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3994. Min Act: -0.1700
Data Index: 4903739 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3682. Min Act: -0.1700
Data Index: 7262081 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3682. Min Act: -0.1700
Data Index: 3799107 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3369. Min Act: -0.1700
Data Index: 3949545 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3369. Min Act: -0.1700
Data Index: 3821648 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3369. Min Act: -0.1700
Data Index: 3047822 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3057. Min Act: -0.1700
Data Index: 6256018 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3057. Min Act: -0.1700
Data Index: 4148565 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3369. Min Act: -0.1700
Data Index: 6930437 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.3057. Min Act: -0.1700
Data Index: 4450512 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.2744. Min Act: -0.1700
Data Index: 7285989 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.2432. Min Act: -0.1700
Data Index: 1647184 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7119. Min Range: -5.7119
Max Act: 5.2432. Min Act: -0.1700
Data Index: 4289461 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19