Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 657 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7958. Min Range: -9.7958
Max Act: 9.7958. Min Act: -0.1700
Data Index: 4808568 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7958. Min Range: -9.7958
Max Act: 9.2958. Min Act: -0.1700
Data Index: 5478034 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7958. Min Range: -9.7958
Max Act: 9.1708. Min Act: -0.1700
Data Index: 8448714 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7958. Min Range: -9.7958
Max Act: 9.0458. Min Act: -0.1700
Data Index: 8245849 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.9833. Min Act: -0.1700
Data Index: 5890783 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.9833. Min Act: -0.1700
Data Index: 1884128 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.9833. Min Act: -0.1700
Data Index: 2726868 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.8583. Min Act: -0.1700
Data Index: 4853669 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.9208. Min Act: -0.1700
Data Index: 7642369 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.9208. Min Act: -0.1700
Data Index: 4917289 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.9208. Min Act: -0.1700
Data Index: 43762 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.8583. Min Act: -0.1700
Data Index: 7948966 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.7958. Min Act: -0.1700
Data Index: 3279718 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.7333. Min Act: -0.1700
Data Index: 7245586 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.7333. Min Act: -0.1700
Data Index: 2544126 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.7333. Min Act: -0.1700
Data Index: 6068504 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.7333. Min Act: -0.1700
Data Index: 439125 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.7333. Min Act: -0.1700
Data Index: 2332358 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.6708. Min Act: -0.1700
Data Index: 2206491 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7958. Min Range: -9.7958
Max Act: 8.6083. Min Act: -0.1700
Data Index: 8298177 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19