Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4881 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0698. Min Range: -5.0698
Max Act: 5.0698. Min Act: -0.1700
Data Index: 297679 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.9760. Min Act: -0.1700
Data Index: 2378088 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.9135. Min Act: -0.1700
Data Index: 6244106 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.9135. Min Act: -0.1700
Data Index: 6636123 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.8823. Min Act: -0.1700
Data Index: 5106621 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.8198. Min Act: -0.1700
Data Index: 6150469 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7573. Min Act: -0.1700
Data Index: 2621349 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7573. Min Act: -0.1700
Data Index: 3086488 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7573. Min Act: -0.1700
Data Index: 5867879 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7573. Min Act: -0.1700
Data Index: 6421923 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7573. Min Act: -0.1697
Data Index: 3966821 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7260. Min Act: -0.1700
Data Index: 40709 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7260. Min Act: -0.1700
Data Index: 8267334 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7260. Min Act: -0.1700
Data Index: 8092205 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7260. Min Act: -0.1700
Data Index: 6675917 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7260. Min Act: -0.1700
Data Index: 1199916 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7260. Min Act: -0.1700
Data Index: 1774039 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.7260. Min Act: -0.1700
Data Index: 8293595 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.6948. Min Act: -0.1700
Data Index: 5349587 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0698. Min Range: -5.0698
Max Act: 4.6948. Min Act: -0.1700
Data Index: 2531488 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19