Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.5562. Min Act: -0.1700
Data Index: 5443661 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.3368. Min Act: -0.1700
Data Index: 7475170 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.3368. Min Act: -0.1700
Data Index: 2036227 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.3368. Min Act: -0.1700
Data Index: 3612086 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.3211. Min Act: -0.1700
Data Index: 7187045 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2740. Min Act: -0.1700
Data Index: 143086 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2740. Min Act: -0.1700
Data Index: 5524461 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2583. Min Act: -0.1700
Data Index: 1806909 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2426. Min Act: -0.1700
Data Index: 8120643 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2426. Min Act: -0.1700
Data Index: 2991326 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2426. Min Act: -0.1700
Data Index: 5577998 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2112. Min Act: -0.1700
Data Index: 3900942 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2269. Min Act: -0.1700
Data Index: 3305039 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2269. Min Act: -0.1700
Data Index: 1766117 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2269. Min Act: -0.1700
Data Index: 2129787 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2112. Min Act: -0.1700
Data Index: 3733482 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.1955. Min Act: -0.1700
Data Index: 2342166 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.2112. Min Act: -0.1700
Data Index: 7671723 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.1955. Min Act: -0.1700
Data Index: 4958481 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5562. Min Range: -3.5562
Max Act: 3.1797. Min Act: -0.1700
Data Index: 3794634 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19