Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2582 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.7766. Min Act: -0.1700
Data Index: 670501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6828. Min Act: -0.1700
Data Index: 4594818 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6828. Min Act: -0.1700
Data Index: 4383363 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6828. Min Act: -0.1700
Data Index: 7916098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6516. Min Act: -0.1700
Data Index: 5737512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6516. Min Act: -0.1700
Data Index: 1384616 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6516. Min Act: -0.1700
Data Index: 1958297 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6203. Min Act: -0.1700
Data Index: 1636333 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6203. Min Act: -0.1700
Data Index: 4285205 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6203. Min Act: -0.1700
Data Index: 1060202 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6203. Min Act: -0.1700
Data Index: 7096853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6203. Min Act: -0.1700
Data Index: 3058343 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.6203. Min Act: -0.1700
Data Index: 3004235 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.5891. Min Act: -0.1700
Data Index: 3563004 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.5891. Min Act: -0.1700
Data Index: 4100477 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.5891. Min Act: -0.1700
Data Index: 650982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.5891. Min Act: -0.1700
Data Index: 2056733 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.5891. Min Act: -0.1700
Data Index: 4584534 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.5891. Min Act: -0.1700
Data Index: 2840878 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7766. Min Range: -4.7766
Max Act: 4.5891. Min Act: -0.1700
Data Index: 858772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19