Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7704. Min Act: -0.1700
Data Index: 6798977 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7704. Min Act: -0.1700
Data Index: 85060 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7391. Min Act: -0.1700
Data Index: 8157350 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7391. Min Act: -0.1700
Data Index: 1912855 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7391. Min Act: -0.1700
Data Index: 3035652 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6798987 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7079. Min Act: -0.1700
Data Index: 5330775 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7079. Min Act: -0.1700
Data Index: 6721279 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7391. Min Act: -0.1700
Data Index: 191245 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6766. Min Act: -0.1700
Data Index: 85061 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6766. Min Act: -0.1700
Data Index: 8644891 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.7079. Min Act: -0.1700
Data Index: 4681500 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6766. Min Act: -0.1700
Data Index: 6123907 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6454. Min Act: -0.1700
Data Index: 7504767 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6454. Min Act: -0.1700
Data Index: 8157352 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6454. Min Act: -0.1700
Data Index: 1824394 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6454. Min Act: -0.1700
Data Index: 8355371 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6454. Min Act: -0.1700
Data Index: 8355369 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6454. Min Act: -0.1700
Data Index: 1824395 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7704. Min Range: -5.7704
Max Act: 5.6766. Min Act: -0.1700
Data Index: 7504768 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19