Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1414. Min Range: -6.1414
Max Act: 6.1414. Min Act: -0.1700
Data Index: 3768911 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1414. Min Range: -6.1414
Max Act: 6.1102. Min Act: -0.1700
Data Index: 3748020 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1414. Min Range: -6.1414
Max Act: 6.0789. Min Act: -0.1700
Data Index: 1289940 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1414. Min Range: -6.1414
Max Act: 6.0164. Min Act: -0.1700
Data Index: 684908 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.8914. Min Act: -0.1700
Data Index: 7116922 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.8914. Min Act: -0.1700
Data Index: 2378212 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7664. Min Act: -0.1700
Data Index: 3417604 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.7664. Min Act: -0.1700
Data Index: 8375753 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.6727. Min Act: -0.1700
Data Index: 1628472 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.6414. Min Act: -0.1700
Data Index: 3946535 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.6414. Min Act: -0.1700
Data Index: 1962409 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.6414. Min Act: -0.1700
Data Index: 2422703 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.6102. Min Act: -0.1700
Data Index: 2483032 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.5789. Min Act: -0.1700
Data Index: 180542 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.5477. Min Act: -0.1700
Data Index: 5919025 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.5164. Min Act: -0.1700
Data Index: 5585891 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.5164. Min Act: -0.1700
Data Index: 777500 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.4852. Min Act: -0.1700
Data Index: 13692 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.5164. Min Act: -0.1700
Data Index: 4432272 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1414. Min Range: -6.1414
Max Act: 5.4539. Min Act: -0.1700
Data Index: 2073998 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19