Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 399 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.7552. Min Act: -0.1700
Data Index: 2245569 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.7083. Min Act: -0.1700
Data Index: 383990 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.7239. Min Act: -0.1700
Data Index: 1883519 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6770. Min Act: -0.1700
Data Index: 6574122 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6457. Min Act: -0.1700
Data Index: 4049775 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6613. Min Act: -0.1700
Data Index: 7122955 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6457. Min Act: -0.1700
Data Index: 76974 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6457. Min Act: -0.1700
Data Index: 8700388 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6457. Min Act: -0.1700
Data Index: 8077474 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6300. Min Act: -0.1700
Data Index: 6894183 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.5987. Min Act: -0.1700
Data Index: 2029358 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6144. Min Act: -0.1700
Data Index: 903872 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6144. Min Act: -0.1700
Data Index: 6442373 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6457. Min Act: -0.1700
Data Index: 6363658 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.5674. Min Act: -0.1700
Data Index: 7500074 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6144. Min Act: -0.1700
Data Index: 7032068 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.6300. Min Act: -0.1700
Data Index: 861611 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.5674. Min Act: -0.1700
Data Index: 3142566 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.5831. Min Act: -0.1700
Data Index: 1095306 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7552. Min Range: -3.7552
Max Act: 3.5518. Min Act: -0.1700
Data Index: 7588106 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19