Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 130 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0144. Min Range: -8.0144
Max Act: 8.0144. Min Act: -0.1700
Data Index: 3584586 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.9519. Min Act: -0.1700
Data Index: 4711 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.8894. Min Act: -0.1700
Data Index: 3863025 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.8894. Min Act: -0.1700
Data Index: 7219328 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.8894. Min Act: -0.1700
Data Index: 186904 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.8894. Min Act: -0.1700
Data Index: 8109380 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.8269. Min Act: -0.1700
Data Index: 5240464 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.7956. Min Act: -0.1700
Data Index: 4787767 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.7644. Min Act: -0.1700
Data Index: 5840772 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.7019. Min Act: -0.1700
Data Index: 5990363 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.7019. Min Act: -0.1700
Data Index: 7760832 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.6706. Min Act: -0.1700
Data Index: 1474674 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.6394. Min Act: -0.1700
Data Index: 8162131 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.6081. Min Act: -0.1700
Data Index: 6388388 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.6081. Min Act: -0.1700
Data Index: 3962043 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.5769. Min Act: -0.1700
Data Index: 2700258 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.5144. Min Act: -0.1700
Data Index: 7997508 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.5456. Min Act: -0.1700
Data Index: 3758030 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.5144. Min Act: -0.1700
Data Index: 972517 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0144. Min Range: -8.0144
Max Act: 7.5144. Min Act: -0.1700
Data Index: 2953005 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19