Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.9270. Min Act: -0.1700
Data Index: 3040592 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.9270. Min Act: -0.1700
Data Index: 6882758 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.6457. Min Act: -0.1700
Data Index: 7894716 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.4582. Min Act: -0.1700
Data Index: 1526963 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.3957. Min Act: -0.1700
Data Index: 241047 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.3645. Min Act: -0.1700
Data Index: 3397831 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.3332. Min Act: -0.1700
Data Index: 1775834 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.3020. Min Act: -0.1700
Data Index: 4105398 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.3332. Min Act: -0.1700
Data Index: 3630347 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.3020. Min Act: -0.1700
Data Index: 5515281 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.2707. Min Act: -0.1700
Data Index: 8609404 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.2082. Min Act: -0.1700
Data Index: 8274911 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.2082. Min Act: -0.1700
Data Index: 1210699 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.1770. Min Act: -0.1700
Data Index: 52078 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.1770. Min Act: -0.1700
Data Index: 788276 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.1457. Min Act: -0.1700
Data Index: 6071113 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.1457. Min Act: -0.1700
Data Index: 6385243 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.1145. Min Act: -0.1700
Data Index: 1422909 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.1457. Min Act: -0.1700
Data Index: 6892174 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9270. Min Range: -7.9270
Max Act: 7.1145. Min Act: -0.1700
Data Index: 5794817 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19