Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.3212. Min Act: -0.1700
Data Index: 5269851 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.2900. Min Act: -0.1700
Data Index: 65479 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.2587. Min Act: -0.1700
Data Index: 7627689 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1962. Min Act: -0.1700
Data Index: 329610 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1650. Min Act: -0.1700
Data Index: 8740207 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1650. Min Act: -0.1700
Data Index: 7633395 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1337. Min Act: -0.1700
Data Index: 6940377 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1337. Min Act: -0.1700
Data Index: 2757681 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1337. Min Act: -0.1700
Data Index: 3467795 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1337. Min Act: -0.1700
Data Index: 8817925 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1025. Min Act: -0.1700
Data Index: 3465966 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1025. Min Act: -0.1700
Data Index: 4883850 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1025. Min Act: -0.1700
Data Index: 2761169 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1025. Min Act: -0.1700
Data Index: 3219127 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.1025. Min Act: -0.1700
Data Index: 5373709 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.0712. Min Act: -0.1700
Data Index: 755360 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.0712. Min Act: -0.1700
Data Index: 4346692 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.0712. Min Act: -0.1700
Data Index: 8243229 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.0712. Min Act: -0.1700
Data Index: 1300463 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3212. Min Range: -6.3212
Max Act: 6.0712. Min Act: -0.1700
Data Index: 4893880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19