Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5093 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.9250. Min Act: -0.1700
Data Index: 3609965 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8568. Min Act: -0.1700
Data Index: 4061055 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8396. Min Act: -0.1700
Data Index: 7794422 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8225. Min Act: -0.1700
Data Index: 6665191 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8053. Min Act: -0.1699
Data Index: 2047453 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8053. Min Act: -0.1700
Data Index: 954998 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8053. Min Act: -0.1700
Data Index: 7836393 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8053. Min Act: -0.1700
Data Index: 2590770 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8225. Min Act: -0.1700
Data Index: 3357614 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.8053. Min Act: -0.1700
Data Index: 5013034 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7881. Min Act: -0.1700
Data Index: 1093701 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7881. Min Act: -0.1700
Data Index: 1236994 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7881. Min Act: -0.1700
Data Index: 7692988 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7881. Min Act: -0.1700
Data Index: 6518140 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7709. Min Act: -0.1700
Data Index: 7976918 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7881. Min Act: -0.1700
Data Index: 7061359 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7881. Min Act: -0.1700
Data Index: 3045288 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7881. Min Act: -0.1700
Data Index: 26886 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7709. Min Act: -0.1700
Data Index: 6678269 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9250. Min Range: -1.9250
Max Act: 1.7709. Min Act: -0.1700
Data Index: 6706234 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19