Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.8851. Min Act: -0.1700
Data Index: 3703881 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.6976. Min Act: -0.1700
Data Index: 7238770 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.6664. Min Act: -0.1700
Data Index: 7972153 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.6039. Min Act: -0.1700
Data Index: 7598424 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.6039. Min Act: -0.1700
Data Index: 6583552 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.6039. Min Act: -0.1700
Data Index: 850429 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.5414. Min Act: -0.1700
Data Index: 4062258 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.5414. Min Act: -0.1700
Data Index: 5416723 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.5414. Min Act: -0.1700
Data Index: 8117702 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.5414. Min Act: -0.1700
Data Index: 678122 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.5101. Min Act: -0.1700
Data Index: 8165010 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.4789. Min Act: -0.1700
Data Index: 8325086 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.5101. Min Act: -0.1700
Data Index: 7725394 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.4789. Min Act: -0.1700
Data Index: 3347423 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.4789. Min Act: -0.1700
Data Index: 7681114 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5341461 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.5101. Min Act: -0.1700
Data Index: 3705757 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.4789. Min Act: -0.1700
Data Index: 5709060 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.4789. Min Act: -0.1700
Data Index: 7220156 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8851. Min Range: -5.8851
Max Act: 5.4789. Min Act: -0.1700
Data Index: 7315442 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19