Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.9023. Min Act: -0.1700
Data Index: 2629705 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.8398. Min Act: -0.1700
Data Index: 5687049 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.8398. Min Act: -0.1700
Data Index: 4093884 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.8711. Min Act: -0.1700
Data Index: 299290 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7773. Min Act: -0.1700
Data Index: 3482716 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7461. Min Act: -0.1700
Data Index: 1550566 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7461. Min Act: -0.1700
Data Index: 258690 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 8005821 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.6836. Min Act: -0.1700
Data Index: 8256403 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 5193480 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 4999570 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 4836142 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.7148. Min Act: -0.1700
Data Index: 1826184 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.6523. Min Act: -0.1700
Data Index: 7034654 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.6211. Min Act: -0.1700
Data Index: 2076827 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.6211. Min Act: -0.1700
Data Index: 6704995 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.6211. Min Act: -0.1700
Data Index: 209940 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.6211. Min Act: -0.1700
Data Index: 4174951 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.5898. Min Act: -0.1700
Data Index: 4409305 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9023. Min Range: -4.9023
Max Act: 4.5898. Min Act: -0.1700
Data Index: 6355751 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19