Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.2122. Min Act: -0.1700
Data Index: 3040665 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.2122. Min Act: -0.1700
Data Index: 5597067 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1809. Min Act: -0.1700
Data Index: 1878854 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1809. Min Act: -0.1700
Data Index: 2222097 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.2122. Min Act: -0.1700
Data Index: 4274963 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1184. Min Act: -0.1700
Data Index: 6909757 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1184. Min Act: -0.1700
Data Index: 4876497 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1184. Min Act: -0.1700
Data Index: 6143206 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1184. Min Act: -0.1700
Data Index: 3387800 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1184. Min Act: -0.1700
Data Index: 6041878 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.1184. Min Act: -0.1700
Data Index: 6430006 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0872. Min Act: -0.1700
Data Index: 1656101 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0559. Min Act: -0.1700
Data Index: 5148731 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0247. Min Act: -0.1700
Data Index: 4452647 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0247. Min Act: -0.1700
Data Index: 2679078 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0247. Min Act: -0.1700
Data Index: 3753715 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0247. Min Act: -0.1700
Data Index: 3621918 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0247. Min Act: -0.1700
Data Index: 6938730 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0247. Min Act: -0.1700
Data Index: 7371772 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2122. Min Range: -5.2122
Max Act: 5.0247. Min Act: -0.1700
Data Index: 4974364 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19