Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1035 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.7275. Min Act: -0.1700
Data Index: 6440162 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.7587. Min Act: -0.1700
Data Index: 2981155 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.7275. Min Act: -0.1700
Data Index: 3889325 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.6650. Min Act: -0.1700
Data Index: 1024547 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.6962. Min Act: -0.1700
Data Index: 2898464 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.6650. Min Act: -0.1700
Data Index: 981740 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.6650. Min Act: -0.1700
Data Index: 7629373 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.6337. Min Act: -0.1700
Data Index: 5791541 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.6025. Min Act: -0.1700
Data Index: 6176738 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.6025. Min Act: -0.1700
Data Index: 2650377 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 3296296 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 3022927 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 3423943 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 1793846 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 2469 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 859064 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 2232290 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5400. Min Act: -0.1700
Data Index: 543098 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5712. Min Act: -0.1700
Data Index: 1792353 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7587. Min Range: -4.7587
Max Act: 4.5087. Min Act: -0.1700
Data Index: 4390773 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19