Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2747 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1451. Min Range: -10.1451
Max Act: 10.1451. Min Act: -0.1700
Data Index: 3063671 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1451. Min Range: -10.1451
Max Act: 10.0201. Min Act: -0.1700
Data Index: 6349088 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.8951. Min Act: -0.1700
Data Index: 4357832 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.9576. Min Act: -0.1700
Data Index: 4357831 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.8326. Min Act: -0.1700
Data Index: 3324040 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.8326. Min Act: -0.1700
Data Index: 4213324 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.7701. Min Act: -0.1700
Data Index: 6137243 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.7076. Min Act: -0.1700
Data Index: 953375 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.7076. Min Act: -0.1700
Data Index: 7549322 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.7076. Min Act: -0.1700
Data Index: 8697624 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.6451. Min Act: -0.1700
Data Index: 4697455 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.6451. Min Act: -0.1700
Data Index: 4709747 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.5826. Min Act: -0.1700
Data Index: 8483816 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.7076. Min Act: -0.1700
Data Index: 953372 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.6451. Min Act: -0.1700
Data Index: 2460658 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.5826. Min Act: -0.1700
Data Index: 2990931 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.5826. Min Act: -0.1700
Data Index: 4722975 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.5826. Min Act: -0.1700
Data Index: 7957971 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.5826. Min Act: -0.1700
Data Index: 5344304 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1451. Min Range: -10.1451
Max Act: 9.5826. Min Act: -0.1700
Data Index: 8609719 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19