Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.5274. Min Act: -0.1700
Data Index: 4568175 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.4024. Min Act: -0.1700
Data Index: 7408198 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.3712. Min Act: -0.1700
Data Index: 693796 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.3087. Min Act: -0.1700
Data Index: 6262724 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.2774. Min Act: -0.1700
Data Index: 1778601 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.2462. Min Act: -0.1700
Data Index: 8020299 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1836. Min Act: -0.1700
Data Index: 767493 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1524. Min Act: -0.1700
Data Index: 8162201 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1836. Min Act: -0.1700
Data Index: 71228 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.2149. Min Act: -0.1700
Data Index: 2162755 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.2149. Min Act: -0.1700
Data Index: 2992224 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1836. Min Act: -0.1700
Data Index: 5840246 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1524. Min Act: -0.1700
Data Index: 1932105 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1211. Min Act: -0.1700
Data Index: 8054757 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1211. Min Act: -0.1700
Data Index: 7647203 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1211. Min Act: -0.1700
Data Index: 4762606 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1211. Min Act: -0.1700
Data Index: 3405365 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1211. Min Act: -0.1700
Data Index: 99783 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1211. Min Act: -0.1700
Data Index: 683648 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5274. Min Range: -4.5274
Max Act: 4.1211. Min Act: -0.1700
Data Index: 5050748 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19