Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1267. Min Range: -6.1267
Max Act: 6.1267. Min Act: -0.1700
Data Index: 3478075 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1267. Min Range: -6.1267
Max Act: 6.0329. Min Act: -0.1700
Data Index: 2589179 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1267. Min Range: -6.1267
Max Act: 6.0017. Min Act: -0.1700
Data Index: 2853730 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.9704. Min Act: -0.1700
Data Index: 6474831 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.9392. Min Act: -0.1700
Data Index: 1130848 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.9079. Min Act: -0.1700
Data Index: 2310692 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.9079. Min Act: -0.1700
Data Index: 7515972 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.8767. Min Act: -0.1700
Data Index: 4877285 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.8767. Min Act: -0.1700
Data Index: 1463019 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.8767. Min Act: -0.1700
Data Index: 2930288 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.8767. Min Act: -0.1700
Data Index: 5304551 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.8142. Min Act: -0.1700
Data Index: 7492833 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.7517. Min Act: -0.1700
Data Index: 5468919 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.7517. Min Act: -0.1700
Data Index: 1404172 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.7517. Min Act: -0.1700
Data Index: 1282766 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.7517. Min Act: -0.1700
Data Index: 562922 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.7204. Min Act: -0.1700
Data Index: 7448736 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.7204. Min Act: -0.1700
Data Index: 3834519 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.6892. Min Act: -0.1700
Data Index: 4808311 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1267. Min Range: -6.1267
Max Act: 5.6579. Min Act: -0.1700
Data Index: 1850604 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19