Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2222 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.7707. Min Act: -0.1700
Data Index: 5436438 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.7394. Min Act: -0.1700
Data Index: 5369505 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.7394. Min Act: -0.1700
Data Index: 4329417 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.7082. Min Act: -0.1700
Data Index: 3162341 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.7082. Min Act: -0.1700
Data Index: 7286732 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6769. Min Act: -0.1700
Data Index: 8783108 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6769. Min Act: -0.1700
Data Index: 8592612 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6769. Min Act: -0.1700
Data Index: 6764797 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6769. Min Act: -0.1700
Data Index: 381079 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6769. Min Act: -0.1700
Data Index: 7494605 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6769. Min Act: -0.1700
Data Index: 180032 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6457. Min Act: -0.1700
Data Index: 2386880 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6457. Min Act: -0.1700
Data Index: 8642178 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6769. Min Act: -0.1700
Data Index: 3957661 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6457. Min Act: -0.1700
Data Index: 5957562 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6457. Min Act: -0.1700
Data Index: 8605597 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6144. Min Act: -0.1700
Data Index: 1036446 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6144. Min Act: -0.1700
Data Index: 7257323 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6144. Min Act: -0.1700
Data Index: 4274841 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7707. Min Range: -6.7707
Max Act: 6.6457. Min Act: -0.1700
Data Index: 8825255 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19