Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.5934. Min Act: -0.1700
Data Index: 1183080 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.4997. Min Act: -0.1700
Data Index: 932155 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.4059. Min Act: -0.1700
Data Index: 4425575 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.3434. Min Act: -0.1700
Data Index: 4366830 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.3434. Min Act: -0.1700
Data Index: 3628884 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.3122. Min Act: -0.1700
Data Index: 3055401 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.3122. Min Act: -0.1700
Data Index: 1092362 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.2184. Min Act: -0.1700
Data Index: 1534657 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.1559. Min Act: -0.1700
Data Index: 8526222 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.1247. Min Act: -0.1700
Data Index: 5521949 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.0934. Min Act: -0.1700
Data Index: 3737687 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.0934. Min Act: -0.1700
Data Index: 6422647 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.0622. Min Act: -0.1700
Data Index: 3721251 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.0309. Min Act: -0.1700
Data Index: 6341841 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5934. Min Range: -6.5934
Max Act: 5.9997. Min Act: -0.1700
Data Index: 8145537 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.0622. Min Act: -0.1700
Data Index: 7742939 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5934. Min Range: -6.5934
Max Act: 5.9997. Min Act: -0.1700
Data Index: 150471 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5934. Min Range: -6.5934
Max Act: 5.9997. Min Act: -0.1700
Data Index: 5214675 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5934. Min Range: -6.5934
Max Act: 5.9997. Min Act: -0.1700
Data Index: 2674698 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5934. Min Range: -6.5934
Max Act: 6.0309. Min Act: -0.1700
Data Index: 5590050 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19