Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 688 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.2913. Min Act: -0.1700
Data Index: 1058960 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.2601. Min Act: -0.1700
Data Index: 8247438 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.2288. Min Act: -0.1700
Data Index: 3576502 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.2288. Min Act: -0.1700
Data Index: 4150492 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.1351. Min Act: -0.1700
Data Index: 8247439 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.0726. Min Act: -0.1700
Data Index: 3874658 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2913. Min Range: -5.2913
Max Act: 5.0726. Min Act: -0.1700
Data Index: 8001561 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.9788. Min Act: -0.1700
Data Index: 7622726 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.9476. Min Act: -0.1700
Data Index: 1302498 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8851. Min Act: -0.1700
Data Index: 1715220 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8538. Min Act: -0.1700
Data Index: 4266128 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8851. Min Act: -0.1700
Data Index: 1980162 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8538. Min Act: -0.1700
Data Index: 3787490 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8851. Min Act: -0.1700
Data Index: 4814394 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8538. Min Act: -0.1700
Data Index: 7689716 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8538. Min Act: -0.1700
Data Index: 5513144 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8538. Min Act: -0.1700
Data Index: 6712849 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8226. Min Act: -0.1700
Data Index: 4536312 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8226. Min Act: -0.1700
Data Index: 4958866 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2913. Min Range: -5.2913
Max Act: 4.8538. Min Act: -0.1700
Data Index: 276454 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19