Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5146 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.5702. Min Act: -0.1700
Data Index: 7689697 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.5390. Min Act: -0.1700
Data Index: 5451746 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.5077. Min Act: -0.1700
Data Index: 8775444 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.4140. Min Act: -0.1700
Data Index: 2023837 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.3827. Min Act: -0.1700
Data Index: 4889021 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.2890. Min Act: -0.1700
Data Index: 8001767 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.2577. Min Act: -0.1700
Data Index: 8126847 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.2265. Min Act: -0.1700
Data Index: 5824575 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.2265. Min Act: -0.1700
Data Index: 151252 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.2265. Min Act: -0.1700
Data Index: 8236368 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.1952. Min Act: -0.1700
Data Index: 5717678 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.1640. Min Act: -0.1700
Data Index: 2867945 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.1327. Min Act: -0.1700
Data Index: 3667104 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.1640. Min Act: -0.1700
Data Index: 6199240 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.1015. Min Act: -0.1700
Data Index: 598715 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.1327. Min Act: -0.1700
Data Index: 521892 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.0390. Min Act: -0.1700
Data Index: 8400937 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.0390. Min Act: -0.1700
Data Index: 1952368 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.0390. Min Act: -0.1700
Data Index: 6697112 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5702. Min Range: -7.5702
Max Act: 7.0390. Min Act: -0.1700
Data Index: 538162 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19