Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 511 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.9143. Min Act: -0.1700
Data Index: 2871902 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.9143. Min Act: -0.1700
Data Index: 8394321 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.9455. Min Act: -0.1700
Data Index: 1112012 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.7580. Min Act: -0.1700
Data Index: 1005190 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6643. Min Act: -0.1700
Data Index: 1005189 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6330. Min Act: -0.1700
Data Index: 6243711 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.6018. Min Act: -0.1700
Data Index: 234319 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5393. Min Act: -0.1700
Data Index: 745822 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5705. Min Act: -0.1700
Data Index: 3421432 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5705. Min Act: -0.1700
Data Index: 8041952 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5705. Min Act: -0.1700
Data Index: 7824215 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5705. Min Act: -0.1700
Data Index: 3211430 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5705. Min Act: -0.1700
Data Index: 5990055 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.4768. Min Act: -0.1700
Data Index: 8270882 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5080. Min Act: -0.1700
Data Index: 1436756 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5080. Min Act: -0.1700
Data Index: 7378858 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5393. Min Act: -0.1700
Data Index: 2191285 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5080. Min Act: -0.1700
Data Index: 8200742 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.5080. Min Act: -0.1700
Data Index: 3694202 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9455. Min Range: -5.9455
Max Act: 5.4455. Min Act: -0.1700
Data Index: 1974978 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19