Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3533 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.1099. Min Act: -0.1700
Data Index: 5772526 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.1412. Min Act: -0.1700
Data Index: 5640390 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.0787. Min Act: -0.1700
Data Index: 744494 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.1099. Min Act: -0.1700
Data Index: 6389624 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.1099. Min Act: -0.1700
Data Index: 6516218 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.0787. Min Act: -0.1700
Data Index: 454494 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.0474. Min Act: -0.1700
Data Index: 6877301 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.0474. Min Act: -0.1700
Data Index: 8467843 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9536. Min Act: -0.1700
Data Index: 8775377 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9536. Min Act: -0.1700
Data Index: 2077102 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1412. Min Range: -4.1412
Max Act: 4.0162. Min Act: -0.1700
Data Index: 4453208 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9536. Min Act: -0.1700
Data Index: 4848892 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9536. Min Act: -0.1700
Data Index: 4388965 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9536. Min Act: -0.1700
Data Index: 376930 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9536. Min Act: -0.1700
Data Index: 268460 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9536. Min Act: -0.1700
Data Index: 3723343 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9224. Min Act: -0.1700
Data Index: 5170940 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9224. Min Act: -0.1700
Data Index: 6828341 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.8911. Min Act: -0.1700
Data Index: 5434138 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1412. Min Range: -4.1412
Max Act: 3.9224. Min Act: -0.1700
Data Index: 1027737 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19