Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.4891. Min Act: -0.1700
Data Index: 5573544 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.4891. Min Act: -0.1700
Data Index: 5399237 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.4579. Min Act: -0.1700
Data Index: 8711695 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3954. Min Act: -0.1700
Data Index: 8349312 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3641. Min Act: -0.1700
Data Index: 8336919 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3954. Min Act: -0.1700
Data Index: 8132676 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3954. Min Act: -0.1700
Data Index: 5397793 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3954. Min Act: -0.1700
Data Index: 605580 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3641. Min Act: -0.1700
Data Index: 8145848 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 172288 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 6556095 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 3648225 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 4905272 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 7819958 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 5719052 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 588523 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 7594877 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3016. Min Act: -0.1700
Data Index: 532964 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3329. Min Act: -0.1700
Data Index: 5573545 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4891. Min Range: -5.4891
Max Act: 5.3016. Min Act: -0.1700
Data Index: 4019931 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19