Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 554 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.1853. Min Act: -0.1700
Data Index: 7001060 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.1228. Min Act: -0.1700
Data Index: 5956608 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.0603. Min Act: -0.1700
Data Index: 4605176 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.0603. Min Act: -0.1700
Data Index: 7872790 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.0916. Min Act: -0.1700
Data Index: 402010 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.0291. Min Act: -0.1700
Data Index: 4218174 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.0291. Min Act: -0.1700
Data Index: 632405 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1853. Min Range: -5.1853
Max Act: 5.0291. Min Act: -0.1700
Data Index: 2803619 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9978. Min Act: -0.1700
Data Index: 1320255 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9978. Min Act: -0.1700
Data Index: 4715551 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9978. Min Act: -0.1700
Data Index: 6039725 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9666. Min Act: -0.1700
Data Index: 2027867 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9978. Min Act: -0.1700
Data Index: 4169256 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9666. Min Act: -0.1700
Data Index: 8442962 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 2437186 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 1252261 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9666. Min Act: -0.1700
Data Index: 2542563 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9041. Min Act: -0.1700
Data Index: 4776447 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 5757750 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1853. Min Range: -5.1853
Max Act: 4.9353. Min Act: -0.1700
Data Index: 2213602 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19