Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2466 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.5245. Min Act: -0.1700
Data Index: 120277 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.4462. Min Act: -0.1700
Data Index: 1060524 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.4305. Min Act: -0.1700
Data Index: 5731660 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.3992. Min Act: -0.1700
Data Index: 7066509 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.3992. Min Act: -0.1700
Data Index: 1030899 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.4149. Min Act: -0.1700
Data Index: 6129042 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.3992. Min Act: -0.1700
Data Index: 1281764 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.3835. Min Act: -0.1700
Data Index: 8045446 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.3521. Min Act: -0.1700
Data Index: 1281758 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.3208. Min Act: -0.1700
Data Index: 4388430 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2894. Min Act: -0.1700
Data Index: 7197346 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.3051. Min Act: -0.1700
Data Index: 4194300 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2894. Min Act: -0.1700
Data Index: 5440173 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2894. Min Act: -0.1700
Data Index: 644780 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2894. Min Act: -0.1700
Data Index: 7121873 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2580. Min Act: -0.1700
Data Index: 7502870 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2894. Min Act: -0.1700
Data Index: 1621488 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2580. Min Act: -0.1700
Data Index: 3751039 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2422. Min Act: -0.1700
Data Index: 5737270 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5245. Min Range: -3.5245
Max Act: 3.2422. Min Act: -0.1700
Data Index: 781500 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19