Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.3849. Min Act: -0.1700
Data Index: 4419386 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.2912. Min Act: -0.1700
Data Index: 3562170 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.0724. Min Act: -0.1700
Data Index: 3689304 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.0724. Min Act: -0.1700
Data Index: 8734429 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.1349. Min Act: -0.1700
Data Index: 5423068 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.1037. Min Act: -0.1700
Data Index: 5221313 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.0099. Min Act: -0.1700
Data Index: 8675000 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3849. Min Range: -5.3849
Max Act: 5.0099. Min Act: -0.1700
Data Index: 5016574 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.9474. Min Act: -0.1700
Data Index: 1762658 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.9474. Min Act: -0.1700
Data Index: 5016576 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.9162. Min Act: -0.1700
Data Index: 35079 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8849. Min Act: -0.1700
Data Index: 6048682 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8849. Min Act: -0.1700
Data Index: 5550202 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8849. Min Act: -0.1700
Data Index: 5269632 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8849. Min Act: -0.1700
Data Index: 2666749 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8849. Min Act: -0.1700
Data Index: 2240550 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8849. Min Act: -0.1700
Data Index: 2737716 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8537. Min Act: -0.1700
Data Index: 7031451 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.7912. Min Act: -0.1700
Data Index: 6250715 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3849. Min Range: -5.3849
Max Act: 4.8224. Min Act: -0.1700
Data Index: 3871767 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19