Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.7517. Min Act: -0.1700
Data Index: 3556474 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.6892. Min Act: -0.1700
Data Index: 977283 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.6579. Min Act: -0.1700
Data Index: 8185710 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.6579. Min Act: -0.1700
Data Index: 3738319 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.6267. Min Act: -0.1700
Data Index: 8004662 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.5954. Min Act: -0.1700
Data Index: 3769526 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.5642. Min Act: -0.1700
Data Index: 2007676 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.5642. Min Act: -0.1700
Data Index: 3556475 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.5329. Min Act: -0.1700
Data Index: 180970 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.5017. Min Act: -0.1700
Data Index: 500917 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.5017. Min Act: -0.1700
Data Index: 5042297 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.5017. Min Act: -0.1700
Data Index: 6934551 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.4704. Min Act: -0.1700
Data Index: 7831311 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.4704. Min Act: -0.1700
Data Index: 5847429 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.4704. Min Act: -0.1700
Data Index: 2270746 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.4079. Min Act: -0.1700
Data Index: 3939416 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.3454. Min Act: -0.1700
Data Index: 3441566 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.3767. Min Act: -0.1700
Data Index: 7045732 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.3454. Min Act: -0.1700
Data Index: 5566008 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7517. Min Range: -6.7517
Max Act: 6.3142. Min Act: -0.1700
Data Index: 4882412 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19