Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5039 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.7985. Min Act: -0.1700
Data Index: 7231881 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.7826. Min Act: -0.1700
Data Index: 7231891 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.7507. Min Act: -0.1700
Data Index: 7231870 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.7348. Min Act: -0.1700
Data Index: 7231879 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.7028. Min Act: -0.1700
Data Index: 7231877 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6868. Min Act: -0.1700
Data Index: 7231866 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6868. Min Act: -0.1700
Data Index: 7231880 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6707. Min Act: -0.1700
Data Index: 7231893 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6707. Min Act: -0.1700
Data Index: 7231892 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6547. Min Act: -0.1700
Data Index: 7231860 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6387. Min Act: -0.1700
Data Index: 7231890 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6226. Min Act: -0.1700
Data Index: 7231863 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6226. Min Act: -0.1700
Data Index: 7231864 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6065. Min Act: -0.1700
Data Index: 7231861 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6065. Min Act: -0.1700
Data Index: 7231886 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6065. Min Act: -0.1700
Data Index: 7231872 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6065. Min Act: -0.1700
Data Index: 7231887 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6065. Min Act: -0.1700
Data Index: 7231871 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.6065. Min Act: -0.1700
Data Index: 7231885 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7985. Min Range: -2.7985
Max Act: 2.5904. Min Act: -0.1700
Data Index: 7231875 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19