Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4169 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2517. Min Range: -5.2517
Max Act: 5.2517. Min Act: -0.1700
Data Index: 1673733 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.9079. Min Act: -0.1700
Data Index: 6210608 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.6892. Min Act: -0.1700
Data Index: 3023867 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.6892. Min Act: -0.1700
Data Index: 3133412 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.6579. Min Act: -0.1700
Data Index: 3979685 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 7126363 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5954. Min Act: -0.1700
Data Index: 6012626 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5954. Min Act: -0.1700
Data Index: 17870 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5954. Min Act: -0.1700
Data Index: 5539936 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5642. Min Act: -0.1700
Data Index: 2643572 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5642. Min Act: -0.1700
Data Index: 588903 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5642. Min Act: -0.1700
Data Index: 4230103 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5642. Min Act: -0.1700
Data Index: 2078622 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5642. Min Act: -0.1700
Data Index: 6478630 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5642. Min Act: -0.1700
Data Index: 5758781 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5329. Min Act: -0.1700
Data Index: 5423103 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5329. Min Act: -0.1700
Data Index: 7784447 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5017. Min Act: -0.1700
Data Index: 5933802 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.4704. Min Act: -0.1700
Data Index: 906047 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2517. Min Range: -5.2517
Max Act: 4.5017. Min Act: -0.1700
Data Index: 707167 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19