Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1491 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.9329. Min Act: -0.1700
Data Index: 1047102 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.9329. Min Act: -0.1700
Data Index: 2696550 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.9017. Min Act: -0.1700
Data Index: 1243408 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.8392. Min Act: -0.1700
Data Index: 5347478 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.8392. Min Act: -0.1700
Data Index: 5393797 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.8079. Min Act: -0.1700
Data Index: 8347109 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.7142. Min Act: -0.1700
Data Index: 5447058 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.6829. Min Act: -0.1700
Data Index: 8394010 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.6517. Min Act: -0.1700
Data Index: 7034655 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.6517. Min Act: -0.1700
Data Index: 7681289 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.6517. Min Act: -0.1700
Data Index: 8625911 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.5892. Min Act: -0.1700
Data Index: 3580341 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.5892. Min Act: -0.1700
Data Index: 1604400 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.5579. Min Act: -0.1700
Data Index: 7037669 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.5579. Min Act: -0.1700
Data Index: 7681993 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.5267. Min Act: -0.1700
Data Index: 1109737 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.5267. Min Act: -0.1700
Data Index: 309290 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.5267. Min Act: -0.1700
Data Index: 4565614 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.4642. Min Act: -0.1700
Data Index: 2682129 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9329. Min Range: -5.9329
Max Act: 5.4954. Min Act: -0.1700
Data Index: 7351726 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19