Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1948 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2794. Min Range: -5.2794
Max Act: 5.2794. Min Act: -0.1700
Data Index: 4168108 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2794. Min Range: -5.2794
Max Act: 5.1544. Min Act: -0.1700
Data Index: 810188 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2794. Min Range: -5.2794
Max Act: 5.0919. Min Act: -0.1700
Data Index: 1582877 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2794. Min Range: -5.2794
Max Act: 5.0294. Min Act: -0.1700
Data Index: 3804766 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2794. Min Range: -5.2794
Max Act: 5.0606. Min Act: -0.1700
Data Index: 6304548 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2794. Min Range: -5.2794
Max Act: 5.0606. Min Act: -0.1700
Data Index: 3174759 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.9981. Min Act: -0.1700
Data Index: 7633371 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.9981. Min Act: -0.1700
Data Index: 2740137 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.9981. Min Act: -0.1700
Data Index: 242591 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.9669. Min Act: -0.1700
Data Index: 6549708 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.9669. Min Act: -0.1700
Data Index: 4479221 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.9044. Min Act: -0.1700
Data Index: 518044 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.8731. Min Act: -0.1700
Data Index: 6472643 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.9044. Min Act: -0.1700
Data Index: 5184269 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.8731. Min Act: -0.1700
Data Index: 60154 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.8731. Min Act: -0.1700
Data Index: 324139 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.8731. Min Act: -0.1700
Data Index: 2523543 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.8419. Min Act: -0.1700
Data Index: 812750 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.8106. Min Act: -0.1700
Data Index: 881450 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2794. Min Range: -5.2794
Max Act: 4.8419. Min Act: -0.1700
Data Index: 4676209 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19