Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 446 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.9591. Min Act: -0.1700
Data Index: 7136227 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.9278. Min Act: -0.1700
Data Index: 2679269 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.8341. Min Act: -0.1700
Data Index: 1696411 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.7716. Min Act: -0.1700
Data Index: 6551608 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.7716. Min Act: -0.1700
Data Index: 1921560 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.7403. Min Act: -0.1700
Data Index: 161798 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.7403. Min Act: -0.1700
Data Index: 2824926 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.7091. Min Act: -0.1700
Data Index: 2514782 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6466. Min Act: -0.1700
Data Index: 7574908 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6466. Min Act: -0.1700
Data Index: 7780202 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6153. Min Act: -0.1700
Data Index: 4439664 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6778. Min Act: -0.1700
Data Index: 8818315 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6466. Min Act: -0.1700
Data Index: 911063 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.5841. Min Act: -0.1700
Data Index: 7141438 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6153. Min Act: -0.1700
Data Index: 4389297 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6153. Min Act: -0.1700
Data Index: 5415764 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.5841. Min Act: -0.1700
Data Index: 1695038 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6153. Min Act: -0.1700
Data Index: 8331952 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.6466. Min Act: -0.1700
Data Index: 2783872 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9591. Min Range: -5.9591
Max Act: 5.5841. Min Act: -0.1700
Data Index: 4686673 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19