Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2851. Min Range: -2.2851
Max Act: 2.2851. Min Act: -0.1700
Data Index: 3164666 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2851. Min Range: -2.2851
Max Act: 2.0521. Min Act: -0.1700
Data Index: 330071 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2851. Min Range: -2.2851
Max Act: 2.0521. Min Act: -0.1700
Data Index: 6981311 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2851. Min Range: -2.2851
Max Act: 2.0015. Min Act: -0.1700
Data Index: 497679 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.9846. Min Act: -0.1700
Data Index: 1367885 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8826. Min Act: -0.1700
Data Index: 7733596 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.9507. Min Act: -0.1700
Data Index: 2914764 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8826. Min Act: -0.1700
Data Index: 5777390 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8996. Min Act: -0.1700
Data Index: 931718 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.9167. Min Act: -0.1700
Data Index: 8450755 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8484. Min Act: -0.1700
Data Index: 6015697 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8484. Min Act: -0.1700
Data Index: 5941761 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8826. Min Act: -0.1700
Data Index: 6192841 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8826. Min Act: -0.1700
Data Index: 4652080 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8312. Min Act: -0.1700
Data Index: 7221597 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.7796. Min Act: -0.1700
Data Index: 2872201 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8484. Min Act: -0.1700
Data Index: 2545466 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.7451. Min Act: -0.1700
Data Index: 1609730 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8312. Min Act: -0.1700
Data Index: 4906787 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2851. Min Range: -2.2851
Max Act: 1.8312. Min Act: -0.1700
Data Index: 4657600 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19