Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 560 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 576467 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 4961650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 6185939 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 3312671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8701. Min Act: -0.1700
Data Index: 8636975 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8383. Min Act: -0.1700
Data Index: 4171453 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 7667479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 1119622 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 1831864 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 6203791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8224. Min Act: -0.1700
Data Index: 6522481 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8224. Min Act: -0.1700
Data Index: 5134350 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8542. Min Act: -0.1700
Data Index: 2453416 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.7906. Min Act: -0.1700
Data Index: 6266560 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.7906. Min Act: -0.1700
Data Index: 5582768 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.7906. Min Act: -0.1700
Data Index: 6084743 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.7746. Min Act: -0.1700
Data Index: 1991730 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.7746. Min Act: -0.1700
Data Index: 5440843 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.7746. Min Act: -0.1700
Data Index: 5847079 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8701. Min Range: -2.8701
Max Act: 2.8065. Min Act: -0.1700
Data Index: 2965343 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19