Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.7245. Min Act: -0.1700
Data Index: 7740800 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6604. Min Act: -0.1700
Data Index: 5771642 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6764. Min Act: -0.1700
Data Index: 4021612 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6444. Min Act: -0.1700
Data Index: 5056840 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6283. Min Act: -0.1700
Data Index: 4290891 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6283. Min Act: -0.1700
Data Index: 2367244 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6122. Min Act: -0.1700
Data Index: 4930146 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6122. Min Act: -0.1700
Data Index: 4253894 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6122. Min Act: -0.1700
Data Index: 6162185 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5961. Min Act: -0.1700
Data Index: 5562691 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6122. Min Act: -0.1700
Data Index: 5851515 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6122. Min Act: -0.1700
Data Index: 5026591 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5961. Min Act: -0.1700
Data Index: 658628 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5961. Min Act: -0.1700
Data Index: 2597054 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.6122. Min Act: -0.1700
Data Index: 6201790 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5961. Min Act: -0.1700
Data Index: 1814007 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5961. Min Act: -0.1700
Data Index: 3337409 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5961. Min Act: -0.1700
Data Index: 1404914 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5961. Min Act: -0.1700
Data Index: 1112000 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7245. Min Range: -2.7245
Max Act: 2.5800. Min Act: -0.1700
Data Index: 1456410 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19