Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 859 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.5247. Min Act: -0.1700
Data Index: 77777 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.2122. Min Act: -0.1700
Data Index: 6434591 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.1810. Min Act: -0.1700
Data Index: 660853 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.1810. Min Act: -0.1700
Data Index: 5513572 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.2122. Min Act: -0.1700
Data Index: 7022354 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.2122. Min Act: -0.1700
Data Index: 3790875 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.1810. Min Act: -0.1700
Data Index: 6330014 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5514791 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.1810. Min Act: -0.1700
Data Index: 6953099 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.1185. Min Act: -0.1700
Data Index: 3910151 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.1497. Min Act: -0.1700
Data Index: 3559706 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 7376114 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0560. Min Act: -0.1700
Data Index: 756678 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0872. Min Act: -0.1700
Data Index: 5735787 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 4035551 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 5735796 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 2844680 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0560. Min Act: -0.1700
Data Index: 2459961 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 8011943 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5247. Min Range: -6.5247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 7022351 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19