Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.6810. Min Act: -0.1700
Data Index: 1544620 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.6185. Min Act: -0.1700
Data Index: 6128859 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.6810. Min Act: -0.1700
Data Index: 6933800 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.4935. Min Act: -0.1700
Data Index: 3423156 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.4310. Min Act: -0.1700
Data Index: 1694786 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.3685. Min Act: -0.1700
Data Index: 711482 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.4310. Min Act: -0.1700
Data Index: 1152445 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.3685. Min Act: -0.1700
Data Index: 7637922 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.3060. Min Act: -0.1700
Data Index: 3401362 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.1810. Min Act: -0.1700
Data Index: 7196751 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 650407 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 7136222 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 2453738 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 1951854 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 5363874 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 7661078 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 7278345 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.1810. Min Act: -0.1700
Data Index: 6673515 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.2435. Min Act: -0.1700
Data Index: 3790142 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6810. Min Range: -10.6810
Max Act: 10.1810. Min Act: -0.1700
Data Index: 1782970 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19