Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1502 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.2700. Min Act: -0.1700
Data Index: 2566579 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.2229. Min Act: -0.1700
Data Index: 1515309 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.1757. Min Act: -0.1700
Data Index: 4246901 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.1442. Min Act: -0.1700
Data Index: 5028003 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.1285. Min Act: -0.1700
Data Index: 4402366 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.0812. Min Act: -0.1700
Data Index: 5132581 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.0654. Min Act: -0.1700
Data Index: 1515308 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.0181. Min Act: -0.1700
Data Index: 7292900 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2700. Min Range: -3.2700
Max Act: 3.0023. Min Act: -0.1700
Data Index: 5383823 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9706. Min Act: -0.1700
Data Index: 637073 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9706. Min Act: -0.1700
Data Index: 7966100 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9231. Min Act: -0.1700
Data Index: 5150974 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9231. Min Act: -0.1700
Data Index: 605804 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9073. Min Act: -0.1700
Data Index: 2528075 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9073. Min Act: -0.1700
Data Index: 527841 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9231. Min Act: -0.1700
Data Index: 4461594 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9073. Min Act: -0.1700
Data Index: 646677 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9231. Min Act: -0.1700
Data Index: 7763970 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.9073. Min Act: -0.1700
Data Index: 5438516 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2700. Min Range: -3.2700
Max Act: 2.8914. Min Act: -0.1700
Data Index: 677418 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19