Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.4792. Min Act: -0.1700
Data Index: 2071806 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.2917. Min Act: -0.1700
Data Index: 4289558 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.1354. Min Act: -0.1700
Data Index: 2469785 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.0729. Min Act: -0.1700
Data Index: 2862640 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.1042. Min Act: -0.1700
Data Index: 1114685 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.0729. Min Act: -0.1700
Data Index: 3234697 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.0104. Min Act: -0.1700
Data Index: 945167 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4792. Min Range: -4.4792
Max Act: 4.0104. Min Act: -0.1700
Data Index: 609512 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9792. Min Act: -0.1700
Data Index: 2010672 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9792. Min Act: -0.1700
Data Index: 1579574 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9792. Min Act: -0.1700
Data Index: 3986289 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9479. Min Act: -0.1700
Data Index: 266497 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9479. Min Act: -0.1700
Data Index: 3748683 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9479. Min Act: -0.1700
Data Index: 7484241 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9166. Min Act: -0.1700
Data Index: 8642693 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.8854. Min Act: -0.1700
Data Index: 2519816 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9166. Min Act: -0.1700
Data Index: 3346554 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.9166. Min Act: -0.1700
Data Index: 3368679 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.8854. Min Act: -0.1700
Data Index: 5060021 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4792. Min Range: -4.4792
Max Act: 3.8541. Min Act: -0.1700
Data Index: 3545295 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19