Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1778 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9747. Min Act: -0.1700
Data Index: 1574697 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9435. Min Act: -0.1700
Data Index: 8197586 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9747. Min Act: -0.1700
Data Index: 6712156 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9435. Min Act: -0.1700
Data Index: 1652028 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9122. Min Act: -0.1700
Data Index: 2057986 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9435. Min Act: -0.1700
Data Index: 1748171 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9122. Min Act: -0.1700
Data Index: 8338373 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.9122. Min Act: -0.1700
Data Index: 4566289 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8810. Min Act: -0.1700
Data Index: 3209754 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 3770656 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 6767457 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 147102 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 6974702 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 3356755 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8185. Min Act: -0.1700
Data Index: 1980924 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8497. Min Act: -0.1700
Data Index: 5828755 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8185. Min Act: -0.1700
Data Index: 3747606 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.7872. Min Act: -0.1700
Data Index: 91020 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8185. Min Act: -0.1700
Data Index: 8608713 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9747. Min Range: -4.9747
Max Act: 4.8185. Min Act: -0.1700
Data Index: 5296729 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19