Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.6747. Min Act: -0.1700
Data Index: 3342680 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.5809. Min Act: -0.1700
Data Index: 1399055 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.5497. Min Act: -0.1700
Data Index: 2389769 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.3309. Min Act: -0.1700
Data Index: 8433684 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.2997. Min Act: -0.1700
Data Index: 7786687 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.2684. Min Act: -0.1700
Data Index: 5717918 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.2059. Min Act: -0.1700
Data Index: 5633984 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.2059. Min Act: -0.1700
Data Index: 5194869 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.2372. Min Act: -0.1700
Data Index: 553102 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.1747. Min Act: -0.1700
Data Index: 2007249 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.1747. Min Act: -0.1700
Data Index: 1543172 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.1434. Min Act: -0.1700
Data Index: 3889463 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.1434. Min Act: -0.1700
Data Index: 3468401 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.1122. Min Act: -0.1700
Data Index: 2876112 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.0809. Min Act: -0.1700
Data Index: 354870 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.1122. Min Act: -0.1700
Data Index: 5236302 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.0809. Min Act: -0.1700
Data Index: 3213751 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 5432590 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 7380357 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6747. Min Range: -7.6747
Max Act: 7.0497. Min Act: -0.1700
Data Index: 3442224 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19