Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1713 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4269. Min Range: -6.4269
Max Act: 6.4269. Min Act: -0.1700
Data Index: 1766842 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4269. Min Range: -6.4269
Max Act: 6.3019. Min Act: -0.1700
Data Index: 5887488 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4269. Min Range: -6.4269
Max Act: 6.1769. Min Act: -0.1700
Data Index: 3746753 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4269. Min Range: -6.4269
Max Act: 6.1144. Min Act: -0.1700
Data Index: 2526726 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4269. Min Range: -6.4269
Max Act: 6.0832. Min Act: -0.1700
Data Index: 1538587 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4269. Min Range: -6.4269
Max Act: 6.0519. Min Act: -0.1700
Data Index: 2598959 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.9894. Min Act: -0.1700
Data Index: 7992107 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.9269. Min Act: -0.1700
Data Index: 2707971 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.9269. Min Act: -0.1700
Data Index: 5473436 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8644. Min Act: -0.1700
Data Index: 2464746 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.9269. Min Act: -0.1700
Data Index: 668009 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8957. Min Act: -0.1700
Data Index: 5845685 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8332. Min Act: -0.1700
Data Index: 2085876 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8644. Min Act: -0.1700
Data Index: 6933836 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8332. Min Act: -0.1700
Data Index: 1381275 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8332. Min Act: -0.1700
Data Index: 3667045 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8332. Min Act: -0.1700
Data Index: 5803171 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8332. Min Act: -0.1700
Data Index: 7865779 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8332. Min Act: -0.1700
Data Index: 5658128 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4269. Min Range: -6.4269
Max Act: 5.8019. Min Act: -0.1700
Data Index: 8242237 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19