Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.9737. Min Act: -0.1700
Data Index: 7103175 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.9425. Min Act: -0.1700
Data Index: 5788804 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7550. Min Act: -0.1700
Data Index: 3432579 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7862. Min Act: -0.1700
Data Index: 8498646 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7237. Min Act: -0.1700
Data Index: 3739922 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7237. Min Act: -0.1700
Data Index: 795253 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7862. Min Act: -0.1700
Data Index: 2420841 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7237. Min Act: -0.1700
Data Index: 7941981 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6925. Min Act: -0.1700
Data Index: 67051 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.7237. Min Act: -0.1700
Data Index: 8790458 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6612. Min Act: -0.1700
Data Index: 2688209 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6300. Min Act: -0.1700
Data Index: 7966809 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6300. Min Act: -0.1700
Data Index: 1882845 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6300. Min Act: -0.1700
Data Index: 2819933 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.6300. Min Act: -0.1700
Data Index: 8166928 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.5987. Min Act: -0.1700
Data Index: 1202439 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.5987. Min Act: -0.1700
Data Index: 2986921 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.5987. Min Act: -0.1700
Data Index: 1361497 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.5987. Min Act: -0.1700
Data Index: 4348859 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9737. Min Range: -4.9737
Max Act: 4.5987. Min Act: -0.1700
Data Index: 6664916 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19