Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.8715. Min Act: -0.1700
Data Index: 5945979 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.8238. Min Act: -0.1700
Data Index: 5381761 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.8397. Min Act: -0.1700
Data Index: 7688460 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.8079. Min Act: -0.1700
Data Index: 4109678 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7920. Min Act: -0.1700
Data Index: 2600937 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.8238. Min Act: -0.1700
Data Index: 7688472 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7920. Min Act: -0.1700
Data Index: 1302814 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7761. Min Act: -0.1700
Data Index: 3145375 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7601. Min Act: -0.1700
Data Index: 3077836 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7442. Min Act: -0.1700
Data Index: 6014161 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7601. Min Act: -0.1700
Data Index: 2543540 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7601. Min Act: -0.1700
Data Index: 4046353 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7442. Min Act: -0.1700
Data Index: 8722273 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7601. Min Act: -0.1700
Data Index: 2532261 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7122. Min Act: -0.1700
Data Index: 7688466 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7442. Min Act: -0.1700
Data Index: 7688475 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7442. Min Act: -0.1700
Data Index: 7703749 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7122. Min Act: -0.1700
Data Index: 5678572 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7122. Min Act: -0.1700
Data Index: 7094732 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8715. Min Range: -2.8715
Max Act: 2.7122. Min Act: -0.1700
Data Index: 7688473 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19