Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4231 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1080. Min Range: -6.1080
Max Act: 6.1080. Min Act: -0.1700
Data Index: 3836097 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1080. Min Range: -6.1080
Max Act: 6.0767. Min Act: -0.1700
Data Index: 2330643 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.9830. Min Act: -0.1700
Data Index: 7313859 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.9830. Min Act: -0.1700
Data Index: 4053081 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.9830. Min Act: -0.1700
Data Index: 6411907 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.9517. Min Act: -0.1700
Data Index: 625570 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.9517. Min Act: -0.1700
Data Index: 2204047 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8892. Min Act: -0.1700
Data Index: 7657862 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8892. Min Act: -0.1700
Data Index: 3570172 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8892. Min Act: -0.1700
Data Index: 8790039 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8580. Min Act: -0.1700
Data Index: 6083972 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8580. Min Act: -0.1700
Data Index: 2836623 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8580. Min Act: -0.1700
Data Index: 7657865 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8580. Min Act: -0.1700
Data Index: 1146599 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8267. Min Act: -0.1700
Data Index: 6842240 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8267. Min Act: -0.1700
Data Index: 6793795 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8267. Min Act: -0.1700
Data Index: 7497090 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.8267. Min Act: -0.1700
Data Index: 7275702 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.7955. Min Act: -0.1700
Data Index: 3382934 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1080. Min Range: -6.1080
Max Act: 5.7642. Min Act: -0.1700
Data Index: 880464 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19