Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.5000. Min Act: -0.1700
Data Index: 8805884 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.4375. Min Act: -0.1700
Data Index: 1239934 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.4375. Min Act: -0.1700
Data Index: 5968068 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.4375. Min Act: -0.1700
Data Index: 5379221 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.3750. Min Act: -0.1700
Data Index: 4787937 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.3125. Min Act: -0.1700
Data Index: 7242009 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.3125. Min Act: -0.1700
Data Index: 1856927 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.3125. Min Act: -0.1700
Data Index: 4140900 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.3125. Min Act: -0.1700
Data Index: 6567122 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.3125. Min Act: -0.1700
Data Index: 95636 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.2500. Min Act: -0.1700
Data Index: 5443980 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.2500. Min Act: -0.1700
Data Index: 412969 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.2187. Min Act: -0.1700
Data Index: 3905335 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.1875. Min Act: -0.1700
Data Index: 3189114 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.1875. Min Act: -0.1700
Data Index: 6628791 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.1562. Min Act: -0.1700
Data Index: 6412008 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.1875. Min Act: -0.1700
Data Index: 1438976 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.1562. Min Act: -0.1700
Data Index: 7896605 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.1562. Min Act: -0.1700
Data Index: 5447178 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5000. Min Range: -4.5000
Max Act: 4.1562. Min Act: -0.1700
Data Index: 8396999 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19