Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5884. Min Range: -8.5884
Max Act: 8.5884. Min Act: -0.1700
Data Index: 4836971 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5884. Min Range: -8.5884
Max Act: 8.4009. Min Act: -0.1700
Data Index: 3371654 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5884. Min Range: -8.5884
Max Act: 8.3384. Min Act: -0.1700
Data Index: 5578162 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5884. Min Range: -8.5884
Max Act: 8.3384. Min Act: -0.1700
Data Index: 3712103 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5884. Min Range: -8.5884
Max Act: 8.3384. Min Act: -0.1700
Data Index: 5790749 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5884. Min Range: -8.5884
Max Act: 8.2134. Min Act: -0.1700
Data Index: 8168263 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.8384. Min Act: -0.1700
Data Index: 8051860 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.8384. Min Act: -0.1700
Data Index: 2614118 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.8384. Min Act: -0.1700
Data Index: 7974850 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.8384. Min Act: -0.1700
Data Index: 6131830 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.8384. Min Act: -0.1700
Data Index: 556840 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.7134. Min Act: -0.1700
Data Index: 800665 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.7134. Min Act: -0.1700
Data Index: 722845 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.6509. Min Act: -0.1700
Data Index: 1797681 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.6509. Min Act: -0.1700
Data Index: 5590920 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.6509. Min Act: -0.1700
Data Index: 4526885 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.5884. Min Act: -0.1700
Data Index: 2437197 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.5884. Min Act: -0.1700
Data Index: 2788551 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.5572. Min Act: -0.1700
Data Index: 3892219 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5884. Min Range: -8.5884
Max Act: 7.5259. Min Act: -0.1700
Data Index: 5943987 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19