Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.5857. Min Act: -0.1700
Data Index: 3509319 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.5857. Min Act: -0.1700
Data Index: 7923986 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.5544. Min Act: -0.1700
Data Index: 1482227 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.5544. Min Act: -0.1700
Data Index: 6658583 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.5544. Min Act: -0.1700
Data Index: 4029538 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.5232. Min Act: -0.1700
Data Index: 6547102 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4919. Min Act: -0.1700
Data Index: 5402916 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4919. Min Act: -0.1700
Data Index: 2875088 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4607. Min Act: -0.1700
Data Index: 7267683 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4294. Min Act: -0.1700
Data Index: 505339 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4607. Min Act: -0.1700
Data Index: 4072665 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4607. Min Act: -0.1700
Data Index: 1720122 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4294. Min Act: -0.1700
Data Index: 782350 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4294. Min Act: -0.1700
Data Index: 6379015 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4294. Min Act: -0.1700
Data Index: 1625917 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4294. Min Act: -0.1700
Data Index: 142696 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3982. Min Act: -0.1700
Data Index: 6430218 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4294. Min Act: -0.1700
Data Index: 2997761 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3982. Min Act: -0.1700
Data Index: 1995053 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3982. Min Act: -0.1700
Data Index: 4105822 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19